Publications & Codes

Google Scholar Citations

Recent publications from DBLP. All the full papers can be downloaded from ResearchGate.

Most codes can be downloaded here. For other codes, please contact the first/second author who conducted the experiments.

Some previously collected benchmark datasets:  Benchmark Datasets.rar

If you find these helpful, I would be very grateful if you could kindly cite the relevant papers!


2017

  • Feiping Nie, Rui Zhang, Xuelong Li. A Generalized Power Iteration Method for Solving Quadratic Problem on the Stiefel Manifold. SCIENCE CHINA Information Sciences (SCIS), 60, 112101, 2017.

    GPI.m

    SCIS17 A generalized power iteration method for solving quadratic problem on the Stiefel manifold.pdf

    A very simple algorithm to solve a difficult problem min_{W'W=I} Tr(W'AW-2W'B) based on reweighted method. Experiments indicate the algorithm can find the globally optimal solution. The idea can be used to solve a more general problem: min_{W'W=I} f(W), where f(W) can be any function.

  • Rui Zhang, Feiping Nie*, Xuelong Li. Self-Weighted Supervised Discriminative Feature Selection.

    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), to appear.

  • Rui Zhang, Feiping Nie*, Xuelong Li. Regularized Class-Specific Subspace Classifier.

    IEEE Transactions on Neural Networks and Learning Systems (TNNLS), to appear.

  • Rong Wang, Feiping Nie*, Richang Hong, Xiaojun Chang, Xiaojun Yang, Weizhong Yu. Fast and Orthogonal Locality Preserving Projectionsfor Dimensionality Reduction. IEEE Transactions on Image Processing (TIP), 26(10):5019-5030, 2017.

  • Mengfan Tang, Feiping Nie*, Ramesh Jain. A graph regularized dimension reduction method for out-of-sample data. Neurocomputing, 225:58-63, 2017.

  • Feiping Nie, Zhouyuan Huo, Heng Huang. Joint Capped Norms Minimization for Robust Matrix Recovery. The 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017.

    IJCAI17 Joint Capped Norms Minimization for Robust Matrix Recovery.pdf

    Re-weighted method for capped norm and capped trace norm minimization.

  • Feiping Nie, Jing Li, Xuelong Li. Self-weighted Multiview Clustering with Multiple Graphs. The 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017.

    IJCAI17 Self-weighted Multiview Clustering with Multiple Graphs.pdf

    Multi-view CLR with parameter-free weights learning.

  • Xiaojun Chen, Feiping Nie*, Joshua Zhexue Huang, Min Yang. Scalable Normalized Cut with Improved Spectral Rotation. The 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017.

    IJCAI17 Scalable Normalized Cut with Improved Spectral Rotation.pdf

    A new and more reasonable spectral rotation method.

  • Xiaojun Chen, Feiping Nie*, Guowen Yuan, Joshua Zhexue Huang. Semi-supervised Feature Selection via Rescaled Linear Regression. The 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017.

    IJCAI17 Semi-supervised Feature Selection via Rescaled Linear Regression.pdf

    Learning feature weights for feature selection. Has an interesting connection with L21 norm, the essence of L21 norm is to learn weights for features.

  • Qi Wang, Zequn Qin, Feiping Nie*, Yuan Yuan. Convolutional 2D LDA for Nonlinear Dimensionality Reduction. The 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017.

    IJCAI17 Convolutional 2D LDA for Nonlinear Dimensionality Reduction.pdf

    Nonlinear 2DLDA for dimensionality reduction.

  • Minnan Luo, Lingling Zhang, Feiping Nie*, Xiaojun Chang, Buyue Qian, Qinghua Zheng. Adaptive Semi-supervised Learning with Discriminative Least Squares Regression. The 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017.

    IJCAI17 Adaptive Semi-supervised Learning with Discriminative Least Squares Regression.pdf

    Semi-supervised DisLSR with adaptive semi-supervised learning method.

  • Feiping Nie, Xiaoqian Wang, Heng Huang. Multiclass Capped Lp-Norm SVM for Robust Classifications. The 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, USA, 2017.

    AAAI17 Multiclass Capped Lp-Norm SVM for Robust Classifications.pdf

    Unilateral loss is more suitable for classification while bilateral loss is more suitable for regression. Minimizing capped L1-norm hinge loss function is equivalent to minimizing the classification error on training data.

  • Feiping Nie, Wei Zhu, Xuelong Li. Unsupervised Large Graph Embedding. The 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, USA, 2017.

    AAAI17 Unsupervised Large Graph Embedding.pdf

    LPP and Spectral Regression are equivalent if the similarity matrix of graph is low rank, doubly stochastic, and positive semi-definite. A new fast and parameter-insensitive graph construction method is proposed which can be applied to accelerate any graph based learning method.

  • Feiping Nie, Guohao Cai, Xuelong Li. Multi-view Clustering and Semi-supervised Classification with Adaptive Neighbours. The 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, USA, 2017.

    MLAN_AAAI2017.rar

    AAAI17 Multi-View Clustering and Semi-Supervised Classification with Adaptive Neighbours.pdf

    Parameter-free multiview learning framework for CAN clustering and semi-supervised classification.

  • Xuelong Li, Di Hu, Feiping Nie*. Large Graph Hashing with Spectral Rotation. The 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, USA, 2017.

    AAAI17 Large Graph Hashing with Spectral Rotation.pdf

    As in spectral clustering, spectral rotation is a key step to get the discrete solution, but it was ignored in the previous spectral hashing method.

2016

  • Xiaojun Chang, Feiping Nie*, Sen Wang, Yi Yang and Xiaofang Zhou, Chengqi Zhang. Compound Rank-k Projections for Bilinear Analysis. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 27(7):1502--1513, 2016.

  • Haifeng Zhao, Zheng Wang, Feiping Nie*. Orthogonal least squares regression for feature extraction. Neurocomputing, 216:200-207, 2016.

  • Feiping Nie, Heng Huang. Subspace Clustering via New Low-Rank Model with Discrete Group Structure Constraint. The 25th International Joint Conference on Artificial Intelligence (IJCAI), New York, USA, 2016.

    LRS.m

    rankSubspaceClustering_ijcai16.pdf

    A new reasonable objective function is designed for subspace clustering problem: automatical discovery of the data groups which are distributed on different low-dimensional subspaces.

  • Feiping Nie, Jing Li, Xuelong Li. Parameter-Free Auto-Weighted Multiple Graph Learning: A Framework for Multiview Clustering and Semi-supervised Classification. The 25th International Joint Conference on Artificial Intelligence (IJCAI), New York, USA, 2016.

    AMGL_Code_update.rar

    ijcai16 Parameter-Free Auto-Weighted Multiple Graph Learning.pdf

    A new multiview learning framework, which can automatically learn the weights for different views in a parameter-free manner.

  • Minnan Luo, Feiping Nie*, Xiaojun Chang, Yi Yang, Qinghua Zheng. Avoiding Optimal Mean Robust PCA/2DPCA with Non-greedy L1-norm Maximization. The 25th International Joint Conference on Artificial Intelligence (IJCAI), New York, USA, 2016.

  • Feiping Nie, Wei Zhu, Xuelong Li. Unsupervised Feature Selection with Structured Graph Optimization. The 30th AAAI Conference on Artificial Intelligence (AAAI), Phoenix, USA, 2016.

    SOGFS_aaai16.zip

    AAAI16 Unsupervised Feature Selection with Structured Graph Optimization.pdf

    Learning a graph with optimal structure for unsupervised feature selection.

  • Feiping Nie, Xiaoqian Wang, Michael I. Jordan, Heng Huang. The Constrained Laplacian Rank Algorithm for Graph-Based Clustering. The 30th AAAI Conference on Artificial Intelligence (AAAI), Phoenix, USA, 2016.

    CLR_code.rar

    CLR_aaai16_ready.pdf

    An effective clustering method which directly obtains the clustering result based on the learned similarity matrix, without having to conduct discretization using K-means or spectral rotation. Propose an effective, fast and parameter free graph construction method.

  • Feiping Nie, Hua Wang, Cheng Deng, Xinbo Gao, Xuelong Li, Heng Huang. New L1-Norm Relaxations and Optimizations for Graph Clustering. The 30th AAAI Conference on Artificial Intelligence (AAAI), Phoenix, USA, 2016.

    AAAI16 New L1-Norm Relaxations and Optimizations for Graph Clustering.pdf

    A new and interesting reformulation of Ratio Cut and Normalized Cut, which makes the relaxed solution has clearer clustering structure.

  • Liangchen Liu, Feiping Nie*, Teng Zhang, Arnold Wiliem, Brian Carrington Lovell. Unsupervised automatic attribute discovery method via multi-graph clustering. The 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, 2016.

    ICPR2016_code_release.zip

2015

  • Yi Yang, Zhigang Ma, Feiping Nie*, Xiaojun Chang, Alexander G. Hauptmann. Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization. International Journal of Computer Vision (IJCV), 113(2):113-127, 2015.

    IJCV15 Multi-Class Active Learning by Uncertainty Sampling with Diversity Maximization.pdf

    A simple and convex way to make the selected relevant samples as diverse as possible.

  • Chenping Hou, Feiping Nie, Dongyun Yi, Dacheng Tao. Discriminative Embedded Clustering: A Framework for Grouping High Dimensional Data. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 26(6):1287-1299, 2015.

  • De Wang, Feiping Nie, Heng Huang. Global Redundancy Minimization for Feature Ranking. IEEE Transactions on Knowledge and Data Engineering (TKDE), 27(10):2743-2755, 2015.

  • Hua Wang, Feiping Nie, Heng Huang. Large-Scale Cross-Language Web Page Classification via Dual Knowledge Transfer Using Fast Nonnegative Matrix Tri-Factorization. ACM Transactions on Knowledge Discovery from Data (TKDD), 10(1):1, 2015.

  • Rong Wang, Feiping Nie, Xiaojun Yang, Feifei Gao and Minli Yao. Robust 2DPCA with Non-Greedy L1-Norm Maximization for Image Analysis. IEEE Transactions on Cybernetics (TC), 45(5):1108-1112, 2015.

  • Yang Yang, Zhigang Ma, Yi Yang, Feiping Nie and Heng Tao Shen. Multi-Task Spectral Clustering by Exploring Inter-task Correlation. IEEE Transactions on Cybernetics (TC), 45(5):1069-1080, 2015.

  • Feiping Nie, Hua Wang, Heng Huang, Chris Ding. Joint Schatten p-Norm and Lp-Norm Robust Matrix Completion for Missing Value Recovery. Knowledge and Information Systems (KAIS), 42(3):525--544, 2015.

    LpRtracep_new.m

    KAIS15 Joint Schatten p -norm and Lp -norm robust matrix completion for missing value recovery.pdf

    A robust matrix completion method. Propose efficient algorithm for the proximal problem with Schatten p-norm or Lp-norm.

  • Xiaoqian Wang, Yun Liu, Feiping Nie, Heng Huang. Discriminative Unsupervised Dimensionality Reduction. The 24th International Joint Conference on Artificial Intelligence (IJCAI), 2015.

  • Wenhao Jiang, Feiping Nie, Heng Huang. Robust Dictionary Learning with Capped L1-Norm. The 24th International Joint Conference on Artificial Intelligence (IJCAI), 2015.

  • Jin Huang, Feiping Nie, Heng Huang. A New Simplex Sparse Learning Model to Measure Data Similarity for Clustering. The 24th International Joint Conference on Artificial Intelligence (IJCAI), 2015.

    simplex_code.rar

    eig1.m

    Solve a simplex representation problem with an efficient algorithm.

  • Xiaojun Chang, Feiping Nie, Zhigang Ma, Yi Yang and Xiaofang Zhou. A Convex Formulation for Spectral Shrunk Clustering. The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2015.

  • Yeqing Li, Feiping Nie, Heng Huang, Junzhou Huang. Large-Scale Multi-View Spectral Clustering via Bipartite Graph. The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2015.

  • Shuai Zheng, Xiao Cai, Chris Ding, Feiping Nie, Heng Huang. A Closed Form Solution to Multi-View Low-Rank Regression. The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2015.

  • Hua Wang, Feiping Nie, Heng Huang. Learning Robust Locality Preserving Projection via p-Order Minimization. The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), 2015.

  • Hongchang Gao, Feiping Nie, Heng Huang. Multi-View Subspace Clustering. The 15th International Conference on Computer Vision (ICCV), 2015.

    code.tar.gz

  • Sen Wang, Feiping Nie, Xiaojun Chang, Lina Yao, Xue Li, Quan Z. Sheng. Unsupervised Feature Analysis with Class Margin Optimization. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2015.

  • Hongchang Gao, Feiping Nie, Weidong Cai, Heng Huang. Robust Capped Norm Nonnegative Matrix Factorization. The 21st ACM International Conference on Information and Knowledge Management (CIKM), 2015.

2014

  • Zhigang Ma, Yi Yang, Feiping Nie, Nicu Sebe, Shuicheng Yan, Alexander G. Hauptmann. Harnessing Lab Knowledge for Real-World Action Recognition. International Journal of Computer Vision (IJCV), 109(1-2):60-73, 2014.

    IJCV14 Harnessing Lab Knowledge for Real-World Action Recognition.pdf

    Minimizing the trace norm is essentially a convex relaxation of the shared subspace learning model, which is suitable for multi-task learning.

  • Chenping Hou, Feiping Nie, Xuelong Li, Dongyun Yi, Yi Wu. Joint Embedding Learning and Sparse Regression: A Framework for Unsupervised Feature Selection. IEEE Transactions on Cybernetics (TC), 44(6):793-804, 2014.

    codeforjelsr.zip

    TC14 Joint Embedding Learning and Sparse Regression A Framework for Unsupervised Feature Selection.pdf

    Journal extension of IJCAI'11 with detailed algorithm, further analysis and more experiments.

  • Guorong Wu, Qian Wang, Daoqiang Zhang, Feiping Nie, Heng Huang, Dinggang Shen. A Generative Probability Model of Joint Label Fusion for Multi-Atlas Based Brain Segmentation. Medical Image Analysis (MIA), 18(6):881-890, 2014.

  • Chenping Hou, Feiping Nie, Changshui Zhang, Dongyun Yi, Yi Wu. Multiple Rank Multi-Linear SVM for Matrix Data Classification. Pattern Recognition (PR), 47(1):454-469, 2014.

  • Deguang Kong, Ryohei Fujimaki, Ji Liu, Feiping Nie, Chris Ding. Exclusive Feature Learning on Arbitrary Structures via L12-norm. Advances in Neural Information Processing Systems 27 (NIPS), 2014.

  • NIPS14 Exclusive Feature Learning on Arbitrary Structures via L12-norm.pdf

  • Feiping Nie, Yizhen Huang, Xiaoqian Wang, Heng Huang. New Primal SVM Solver with Linear Computational Cost for Big Data Classifications. The 31st International Conference on Machine Learning (ICML), 2014.

    svm_ALM_new.m

    ICML14 New Primal SVM Solver with Linear Computational Cost for Big Data Classifications.pdf

    A new linear time solver for SVM which can be easily implemented with only several lines of MATLAB code, and can be easily parallelized.

  • Feiping Nie, Jianjun Yuan, Heng Huang. Optimal Mean Robust Principal Component Analysis. The 31st International Conference on Machine Learning (ICML), 2014.

    RPCA_OM.rar

    ICML14 Optimal Mean Robust Principal Component Analysis.pdf

    Consider the optimal mean in robust PCA, which is an easily ignored issue. Propose a very simple algorithm to solve a very general problem.

  • Hua Wang, Feiping Nie, Heng Huang. Robust Distance Metric Learning via Simultaneous L1-Norm Minimization and Maximization. The 31st International Conference on Machine Learning (ICML), 2014.

    ICML14 Robust Distance Metric Learning via Simultaneous L1-Norm Minimization and Maximization.pdf

    The general ratio problem f(x)/g(x) can be optimized by iteratively solving the difference problem f(x)-r*g(x). It can be proved that the convergence rate is quadratic.

  • Feiping Nie, Xiaoqian Wang, Heng Huang. Clustering and Projected Clustering with Adaptive Neighbors. The 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), New York, USA, 2014.  

    CODE   SLIDES

    KDD14 Clustering and Projected Clustering with Adaptive Neighbors.pdf

    Solving a challenging and fundamental clustering problem with elegant optimization and with amazing performance!

  • De Wang*, Feiping Nie*, Heng Huang. Large-Scale Adaptive Semi-Supervised Learning via Unified Inductive and Transductive Model. The 20th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), New York, USA, 2014.

    ASL.m

    KDD14 Large-Scale Adaptive Semi-Supervised Learning via Unified Inductive and Transductive Model.pdf

    Only one parameter r, which has multiple properties: 1. From macro view, r controls the weight of unlabeled data (larger r, less weight). 2. From micro view, given r, uncertain data lying around boundary have negligible weights (more uncertain, less weight).

  • Xiaojun Chang, Feiping Nie, Yi Yang, Heng Huang. A Convex Formulation for Semi-Supervised Multi-Label Feature Selection. The Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI), Quebec, Canada, USA, 2014.

    CSFS.m

    AAAI14 A Convex Formulation for Semi-Supervised Multi-Label Feature Selection.pdf

    A convex formulation to learn labels and projections simultaneously, which can be used for large scale data.

  • Hua Wang, Feiping Nie, Heng Huang. Globally and Locally Consistent Unsupervised Projection. The Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI), Quebec, Canada, USA, 2014.

    AAAI14 Globally and Locally Consistent Unsupervised Projection.pdf

    A simple unsupervised dimensionality reduction method: maximize variance and minimize local variance simultaneously via trace ratio criterion. The only parameter is the number of neighbors.

  • Hua Wang, Feiping Nie, Heng Huang. Video Recovery via Low-Rank Tensor Completion with Spatio-Temporal Consistency. The Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI), Quebec, Canada, USA, 2014.

  • Miao Zhang, Chris Ding, Ya Zhang, Feiping Nie. Feature Selection at the Discrete Limit. The Twenty-Eighth AAAI Conference on Artificial Intelligence (AAAI), Quebec, Canada, USA, 2014.

    An efficient coordinate descent method for L2p norm minimization.

    AAAI14 Feature Selection at the Discrete Limit.pdf

  • De Wang, Yang, Wang, Feiping Nie, Jingwen Yan, Andew Saykin, Li Shen, Heng Huang. Human Connectome Module Pattern Detection Using A New Multi-Graph MinMax Cut Model. The 17th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Boston, USA, 2014.

  • Feiping Nie, Xiao Cai, Heng Huang. Flexible Shift-Invariant Locality and Globality Preserving Projections. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Nancy, France, 2014.

    FLGPP.m

    ECML PKDD14 Flexible Shift-Invariant Locality and Globality Preserving Projections.pdf

    A new shift invariant LPP with flexible linear constraint. A novel algorithm to solve this difficult problem with proved optimal solution. It is worth to note that in LPP, the X*D*X' should be X*L_D*X' (L_D is another Laplacian matrix), otherwise the data MUST be centerized before using LPP.

  • De Wang, Feiping Nie, Heng Huang. Unsupervised Feature Selection via Unified Trace Ratio Formulation and K-means Clustering (TRACK). The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Nancy, France, 2014.

    TRACK.rar

    ECML PKDD14 Unsupervised Feature Selection via Unified Trace Ratio Formulation and K-means Clustering (TRACK).pdf

    A compact optimization problem to which the solution is exactly the procedure of iterative Kmeans+trace ratio LDA. It can be used for unsupervised dimensionality reduction, clustering, and feature selection.

2013
  • Chenping Hou, Feiping Nie, Dongyun Yi, Yi Wu. Efficient Image Classification via Multiple Rank Regression. IEEE Transactions on Image Processing (TIP), 22(1):340-352, 2013.

    TIP-MRR.rar

    Propose a new 2D (or tensor) method, which trades off the learning ability and generalization. Traditional 2D method: weakest learning ability but best generalization. 1D method: best learning ability but weakest generalization.

  • Jin Huang, Feiping Nie, Heng Huang, Chris Ding. Robust Manifold Non-Negative Matrix Factorization. ACM Transactions on Knowledge Discovery from Data (TKDD), 8(3):11, 2013.  

    RMNMF.rar

    TKDD13 Robust Manifold Nonnegative Matrix Factorization.pdf

    Propose a new Laplacian regularized NMF method with non-trivial solution.

  • Jin Huang, Feiping Nie, Heng Huang, Yicheng Tu, Yu Lei. Social Trust Prediction Using Heterogeneous Networks. ACM Transactions on Knowledge Discovery from Data (TKDD), 7(4):17, 2013.

    CDCF.m

  • Yun Liu, Feiping Nie*, Jigang Wu, Lihui Chen. Efficient Semi-supervised Feature Selection with Noise Insensitive Trace Ratio Criterion. Neurocomputing, 105:12-18, 2013.

    TRCFS_semi.m

    NCI13 Efficient Semi-supervised Feature Selection with Noise Insensitive Trace Ratio Criterion.pdf

    Analyze the noise influence to the trace ratio criterion for feature selection. Propose a simple and reasonable feature normalization approach for feature selection.

  • Chenping Hou, Feiping Nie, Changshui Zhang, Yi Wu. Learning a Subspace for Clustering via Pattern Shrinking. Information Processing & Management (IPM), 49(4):871-883, 2013.  

    IPM.rar

  • Feiping Nie, Dong Xu, Ivor W. Tsang, Changshui Zhang. A Flexible and Effective Linearization Method for Subspace Learning. Book Chapter, 2013.  

    FME.zip

    book chapter A Flexible and Effective Linearization Method.pdf

    Invited book chapter for the FME framework.

  • Hua Wang, Feiping Nie, Heng Huang. Robust and Discriminative Self-Taught Learning. The 30th International Conference on Machine Learning (ICML), 2013.

  • Hua Wang, Feiping Nie, Heng Huang. Multi-View Clustering and Feature Learning via Structured Sparsity. The 30th International Conference on Machine Learning (ICML), 2013.

    ICML13 Multi-View Clustering and Feature Learning via Structured Sparsity.pdf

    Propose a multi-view norm (group L1 norm) for multi-view feature learning.

  • Xiao Cai, Chris Ding, Feiping Nie, Heng Huang. On The Equivalent of Low-Rank Linear Regressions and Linear Discriminant Analysis Based Regressions. The 19th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2013.  

    LeastSquareLDA_lowrank.rar

    KDD13 On The Equivalence of Low-Rank Regression and Discriminant Analysis.pdf

    Reveal that LDA which extracts k features can be viewed as rank k Least squares regression.

  • Jin Huang, Feiping Nie, Heng Huang, Yu Lei, Chris Ding. Social Trust Prediction Using Rank-k Matrix Recovery. The 23rd International Joint Conference on Artificial Intelligence (IJCAI), 2013.

    robustMC_rankK.m

    Robust matrix completion method with rank-k constraint without tuning the regularization parameter.

  • Feiping Nie, Hua Wang, Heng Huang, Chris Ding. Early Active Learning via Robust Representation and Structured Sparsity. The 23rd International Joint Conference on Artificial Intelligence (IJCAI), 2013.

    RRSS_activelearning.m

    IJCAI13 Early Active Learning via Robust Representation and Structured Sparsity.pdf

    A convex and robust active learning method with cold start.

  • Feiping Nie, Hua Wang, Heng Huang, Chris Ding. Adaptive Loss Minimization for Semi-Supervised Elastic Embedding. The 23rd International Joint Conference on Artificial Intelligence (IJCAI), 2013.

    SEE.m

    IJCAI13 Adaptive Loss Minimization for Semi-Supervised Elastic Embedding.pdf

    An adaptive loss function is proposed. It behaves between L1 loss and L2 loss, and enjoys many elegant properties.

  • Xiao Cai, Feiping Nie, Heng Huang. Exact Top-k Feature Selection via l2,0-Norm Constraint. The 23rd International Joint Conference on Artificial Intelligence (IJCAI), 2013.

    FSRobust_ALM.m

    IJCAI13 Exact Top-k Feature Selection via l2,0-Norm Constraint.pdf

    A feature selection method without tuning the regularization parameter, which is achieved by solving a L20 constrained problem.

  • Xiao Cai, Feiping Nie, Heng Huang. Multi-View K-Means Clustering on Big Data. The 23rd International Joint Conference on Artificial Intelligence (IJCAI), 2013.

    weighted_robust_multi_kmeans.m

    A multi-view robust K-means method, which is as fast as K-means algorithm.

  • Zhigang Ma, Yi Yang, Feiping Nie, Sebe Nicu. Thinking of Images as What They Are: Compound Matrix Regression for Image Classification. The 23rd International Joint Conference on Artificial Intelligence (IJCAI), 2013.

  • Jin Huang, Feiping Nie, Heng Huang, Chris Ding. Supervised and Projected Sparse Coding for Image Classification. The Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2013.

    SupervisedSparseCoding.m

    Projected sparse representation for simultaneously dimensionality reduction and classification. The idea can be easily extended to unsupervised learning.

  • Jin Huang, Feiping Nie, Heng Huang. Robust Discrete Matrix Completion. The Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2013.  

    robustDMC.m

  • Jin Huang, Feiping Nie, Heng Huang. Spectral Rotation vs K-means in Spectral Clustering. The Twenty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2013.  

    SRvsKM.m

    AAAI13 Spectral Rotation vs K-means in Spectral Clustering.pdf

    Theoretically understand why Spectral Rotation (SR) is better than K-means in the spectral clustering with spectral relaxation.

  • Hua Wang, Feiping Nie, Heng Huang. Heterogeneous Visual Features Fusion via Sparse Multimodal Machine. The 26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013.

  • Hua Wang, Feiping Nie, Weidong Cai, Heng Huang. Semi-Supervised Robust Dictionary Learning via Efficient l2,0+-Norms Minimization. International Conference on Computer Vision (ICCV), 2013.

    Propose a very simple method to minimize the L2p norm function.

  • Xiao Cai, Feiping Nie, Weidong Cai, Heng Huang. New Graph Structured Sparsity Model for Multi-Label Image Annotations. International Conference on Computer Vision (ICCV), 2013.

    L2G21_new.m

    A new sparse model for multi-label learning, which can also be used for multi-task learning.

  • Xiao Cai, Feiping Nie, Weidong Cai, Heng Huang. Heterogeneous Image Features Integration via Multi-Modal Semi-Supervised Learning Model. International Conference on Computer Vision (ICCV), 2013.  

    weightMMSSL.m

    ICCV13 Heterogeneous Image Feature Integration via Multi-Modal Semi-Supervised Learning for Image Categorization.pdf

    A multi-view semi-supervised learning method with adaptive weights on different views.

  • De Wang, Feiping Nie, Heng Huang, Jingwen Yan, Shannon Risacher, Andrew Saykin, Li Shen. Structural Brain Network Constrained Neuroimaging Marker Identification for Predicting Cognitive Functions.  The International Conference on Information Processing in Medical Imaging (IPMI), 2013.

  • Heng Huang, Jingwen Yan, Feiping Nie, Jin Huang, Weidong Cai, Andrew J. Saykin, Li Shen. A New Sparse Learning Model for Brain Anatomical and Genetic Network Analysis. The 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nagoya, Japan, 2013.

    Propose a simple root finding algorithm to solve the proximal problem: min_{x>=0,x'*1=1} ||x-v||^2.

  • Guorong Wu, Feiping Nie, Qian Wang, Shu Liao, Daoqiang Zhang, and Dinggang Shen. Minimizing Joint Risk of Mislabeling for Iterative Patch-based Label Fusion. The 16th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nagoya, Japan, 2013.

2012
  • Yi Yang, Feiping Nie, Dong Xu, Jiebo Luo, Yueting Zhuang, Yunhe Pan. A Multimedia Retrieval Framework based on Semi-Supervised Ranking and Relevance Feedback.  IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 34(4):723-742, 2012.  

    LRGA_ranking.rar

    TPAMI12 A Multimedia Retrieval Framework based on Semi-Supervised Ranking and Relevance Feedback.pdf

    Journal extension of ACM MM'09 with detailed algorithm, further analysis and more applications.

  • Yi Yang, Fei Wu, Feiping Nie, Heng Tao Shen, Yueting Zhuang, Alexander G. Hauptmann. Web & Personal Image Annotation by Mining Label Correlation with Relaxed Visual Graph Embedding.  IEEE Transactions on Image Processing (TIP), 21(3):1339-1351, 2012.  

    LGME.m

    FME with shared subspace model for semi-supervised multi-label learning, which has closed form solution. Shared subspace model is essentially a low rank (rank k) linear regression, so the proposed method can also be used for multi-task learning.

  • Shiming Xiang, Feiping Nie, Gaofeng Meng, Chunhong Pan, Changshui Zhang. Discriminative Least Squares Regression for Multiclass Classification and Feature Selection.  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 42(1):17-27, 2012.  

    Code of Discriminative Least Squares Regression.rar

    TNNLS12 Discriminative Least Squares Regression for Multiclass Classification and Feature Selection.pdf

    A novel and interesting formulation to make the least squares regression suitable for classification.

  • Yi Huang, Dong Xu, Feiping Nie. Semi-supervised Dimension Reduction using Trace Ratio Criterion.  IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 23(3): 519-526, 2012.  

    TR_FSDA.m

    Semi-supervised dimension reduction with flexible linearization. A novel algorithm is proposed to find the globally optimal solution.

  • Feiping Nie, Dong Xu, Xuelong Li. Initialization Independent Clustering with Actively Self-Training Method.  IEEE Transactions on Systems, Man and Cybernetics, Part B (TSMCB), 42(1):17-27, 2012.  

    ASTC.m

    TSMCB12 Initialization Independent Clustering with Actively Self-Training Method.pdf

    Actively find the most representative points and then perform semi-supervised classification based on the pseudo labels. It can be used for a special semi-supervised clustering (labeled classes < c), and can also be used for single or batch mode active learning.

  • Yi Huang, Dong Xu, Feiping Nie. Patch Distribution Compatible Semi-Supervised Dimension Reduction for Face and Human Gait Recognition.  IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 22(3):479-488, 2012.

  • Zhigang Ma, Feiping Nie, Yi Yang, Jasper Uijlings, Nicu Sebe, Alexander G. Hauptmann. Discriminating Joint Feature Analysis for Multimedia Content Understanding.  IEEE Transactions on Multimedia (TMM), 14(6):1662-1672, 2012.  

    semisupervised_feature_slection.zip

    Journal extension of ACM MM'11 (semi-supervised feature selection) with more analysis and experiments.

  • Zhigang Ma, Feiping Nie, Yi Yang, Jasper Uijlings, Nicu Sebe. Web Image Annotation via Subspace-Sparsity Collaborated Feature Selection.  IEEE Transactions on Multimedia (TMM), 14(4):1021-1030, 2012.  

    subspace_J21.m

    Shared subspace model for multi-label feature selection. Shared subspace model is essentially a low rank (rank k) linear regression, so the proposed method can also be used for multi-task feature selection.

  • Hua Wang, Feiping Nie, Heng Huang, Jingwen Yan, Sungeun Kim, Kwangsik Nho, Shannon L. Risacher, Andrew J. Saykin, Li Shen, ADNI. From Phenotype to Genotype: An Association Study of Candidate Phenotypic Markers to Alzheimer's Disease Relevant SNPs.  Bioinformatics, 28(18): i619-i625, 2012.

  • Hua Wang, Feiping Nie, Heng Huang, Shannon L. Risacher, Andrew J. Saykin, Li Shen, ADNI. Identifying Disease Sensitive and Quantitative Trait Relevant Biomarkers from Multi-Dimensional Heterogeneous Imaging Genetics Data via Sparse Multi-Modal Multi-Task Learning. Bioinformatics, 28(12): i127-i136, 2012.

    Group L1 norm (adaptively select specific views for specific task) and L21 norm (pursuing joint sparsity between tasks) for multi-modal (view) multi-task learning.

  • Hua Wang, Feiping Nie, Heng Huang, Sungeun Kim, Kwangsik Nho, Shannon Risacher, Andrew J Saykin, Li Shen, ADNI. Identifying Quantitative Trait Loci via Group-Sparse Multi-Task Regression and Feature Selection: An Imaging Genetics Study of the ADNI Cohort.  Bioinformatics, 28(2): 229-237, 2012.

  • Feiping Nie, Shiming Xiang, Yun Liu, Chenping Hou, Changshui Zhang. Orthogonal vs. Uncorrelated Least Squares Discriminant Analysis for Feature Extraction.  Pattern Recognition Letters (PRL), 33(5): 485-491, 2012.  

    OLSLDA.m

    PRL12 Orthogonal vs. Uncorrelated Least Squares Discriminant Analysis for Feature Extraction.pdf

    An iteresting reformulation to Tr(W'*Sw*W).

  • Shizhun Yang, Chenping Hou, Feiping Nie, Yi Wu. Unsupervised maximum margin feature selection via L2,1-norm minimization. Neural Computing & Applications (NCA), 21(7):1791-1799, 2012.

    UMMFSSC.m

    NCA12 Unsupervised maximum margin feature selection via L2,1-norm minimization.pdf

  • Hua Wang, Feiping Nie, Heng Huang, Jingwen Yan, Sungeun Kim, Shannon Risacher, Andrew Saykin, Li Shen. High-Order Multi-Task Feature Learning to Identify Longitudinal Phenotypic Markers for Alzheimer Disease Progression Prediction. The Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, Nevada, USA, 2012. Oral Paper.  (Acceptance Rate 20/1467=1.4%)

    A novel tensor linear regression for multi-task feature learning.

  • Dijun Luo, Chris Ding, Heng Huang, Feiping Nie. Forging The Graphs: A Low Rank and Positive Semidefinite Graph Learning Approach. The Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS), Lake Tahoe, Nevada, USA, 2012.

    NIPS12 Forging The Graphs A Low Rank and Positive Semidefinite Graph Learning Approach.pdf

    A convex graph learning method is proposed. Give a simple solution to the proximal problem under the constraints on singular values of matrix.

  • Deguang Kong, Chris Ding, Heng Huang, Feiping Nie. An Iterative Locally Linear Embedding Algorithm. The 29th International Conference on Machine Learning (ICML), 2012.  

    ICML 2012 PAPER CODE_dkong.zip

  • Feiping Nie, Heng Huang, Chris Ding. Efficient Schatten-p Norm Minimization for Low-Rank Matrix Recovery. The 26th AAAI Conference on Artificial Intelligence (AAAI), Toronto, Ontario, Canada, 2012.  

    Schatten p code.rar

    AAAI12 Efficient Schatten-p Norm Minimization for Low-Rank Matrix Recovery.pdf

    Propose a very simple method to minimize the Schatten-p norm function.

  • Hua Wang, Feiping Nie, Heng Huang. Robust and Discriminative Distance for Multi-Instance Learning. The 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, USA, 2012.

    A discriminative Class-to-Bag (C2B) distance is proposed for multi-instance learning.

  • Hua Wang, Feiping Nie, Heng Huang, Chris Ding. Predicting Protein-Protein Interactions from Multimodal Biological Data Sources via Nonnegative Matrix Factorization. The 16th International Conference on Research in Computational Molecular Biology (RECOMB) , Barcelona, Spain, 2012. (acceptance rate <15.5%, 31/200+)

  • Hanbo Chen, Xiao Cai, Dajiang Zhu, Feiping Nie, Tianming Liu, Heng Huang. Group-wise Consistent Parcellation of Gyri via Adaptive Multi-view Spectral Clustering of Fiber Shapes. The 15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Nice, France, 2012.

  • Feiping Nie, Hua Wang, Xiao Cai, Heng Huang, Chris Ding. Robust Matrix Completion via Joint Schatten p-Norm and Lp-Norm Minimization. IEEE International Conference on Data Mining (ICDM), Brussels, Belgium, 2012.  

    The paper indictates that ALM algorithm can be used to solve most difficult problems. It is one of the best conference papers selected for extension to KAIS journal.

    LpRtracep.m

    ICDM12 Robust Matrix Completion via Joint Schatten p-Norm and Lp-Norm Minimization.pdf

  • Jin Huang, Feiping Nie, Heng Huang, Yicheng Tu. Trust Prediction via Aggregating Heterogeneous Social Networks.  The 21st ACM International Conference on Information and Knowledge Management (CIKM), 2012.

    CDCF.m  

2011

  • Feiping Nie, Zinan Zeng, Ivor Tsang, Dong Xu, Changshui Zhang. Spectral Embedded Clustering: A  Framework for In-Sample and Out-of-Sample Spectral Clustering.  IEEE Transactions on Neural Networks (TNN), 22(11):1796-1808, 2011.  

    SEC.m

    TNN11 Spectral Embedded Clustering A Framework for In-Sample and Out-of-Sample Spectral Clustering.pdf

    Journal extension of IJCAI'09 with detailed algorithm and further analysis. It points out that the eigenvector associated with the eigenvalue 0 of the Laplacian matrix should not be discarded in spectral rotation.

  • Chenping Hou, Feiping Nie, Fei Wang, Changshui Zhang, Yi Wu. Semi-Supervised Learning Using Negative Labels.  IEEE Transactions on Neural Networks (TNN), 22(3):420-432, 2011.  

    TNN-NLP.rar

    A new weak supervised information (a sample doesn't belong to certain class) is proposed to use for semi-supervised learning.

  • Cheng Chen, Yueting Zhuang, Feiping Nie, Yi Yang, Fei Wu, Jun Xiao. Learning a 3D Human Pose Distance Metric from Geometric Pose Descriptor.  IEEE Transactions on Visualization and Computer Graphics (TVCG), 17(11):1676-1689, 2011.

  • Shiming Xiang, Feiping Nie, Chunhong Pan, Changshui Zhang. Regression Reformulations of LLE and LTSA with Locally Linear Transformation.  IEEE Transactions on Systems, Man and Cybernetics, Part B (TSMCB), 41(5):1250-1262, 2011.

    TSMCB11 Regression Reformulations of LLE and LTSA with Locally Linear Transformation.pdf

    Uncover the very close connection between LLE and LTSA, from which understand why LTSA is better than LLE for manifold learning.

  • Feiping Nie, Dong Xu, Xuelong Li, Shiming Xiang. Semi-Supervised Dimensionality Reduction and Classification through Virtual Label Regression.  IEEE Transactions on Systems, Man and Cybernetics, Part B (TSMCB), 41(3):675-685, 2011.  

    semi_LS_SubspaceL.m

    TSMCB11 Semi-Supervised Dimensionality Reduction and Classification through Virtual Label Regression.pdf

    A special weighted linear regression with virtual labels is developed for semi-supervised learning.

  • Shiming Xiang, Chunhong Pan, Feiping Nie, Changshui Zhang. Interactive Image Segmentation with Multiple Linear Reconstructions in Windows. IEEE Transactions on Multimedia (TMM), 13(2):342-352, 2011.  

    slrw.rar

  • Cheng Chen, Yi Yang, Feiping Nie, Jean-Marc Odobez. 3D Human Pose Recovery from Monocular Images via Efficient Visual Feature Selection. Computer Vision and Image Understanding (CVIU), 115(3):290-299, 2011.

  • Hua Wang, Heng Huang, Farhad Kamangar, Feiping Nie, Chris Ding.  Maximum Margin Multi-Instance Learning. The Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), Granada, Spain, 2011.

    Propose a Class-to-Bag (C2B) distance for Multi-Instance Learning (MIL).

  • Dijun Luo, Chris Ding, Feiping Nie, Heng Huang. Cauchy Graph Embedding. The 28th International Conference on Machine Learning (ICML), Bellevue, 2011.  (Acceptance Rate: 152/598=25.4%).  

    CauchyEmbedding.m

    ICML11 Cauchy Graph Embedding.pdf

    A Cauchy embedding is proposed beyond the Laplacian embedding.

  • Hua Wang, Feiping Nie, Heng Huang, Fillia Makedon. Fast Nonnegative Matrix Tri-Factorization for Large-Scale Data Co-Clustering. The 22nd International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, 2011. (Acceptance Rate:227/1325=17.1%).

    co-kmeans code.rar

    IJCAI11 Fast Nonnegative Matrix Tri-Factorization for Large-Scale Data Co-Clustering.pdf

    A novel co-Kmeans algorithm is proposed for co-clustering, which is as fast as Kmeans.

  • Feiping Nie, Heng Huang, Chris Ding, Dijun Luo, Hua Wang. Robust Principal Component Analysis with Non-Greedy L1-Norm Maximization. The 22nd International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, 2011. (Acceptance Rate:(227+173)/1325=30.2%).  

    PCA_norm1_nongreedy.m

    ijcai11 Robust Principal Component Analysis with Non-Greedy l1-Norm Maximization.pdf

    A very simple algorithm to solve a general L1 norm maximization problem.

  • Chenping Hou, Feiping Nie, Dongyun Yi, Yi Wu. Feature selection via joint embedding learning and sparse regression. The 22nd International Joint Conference on Artificial Intelligence (IJCAI), Barcelona, 2011. (Acceptance Rate:(227+173)/1325=30.2%).  

    codeforjelsr.zip

    A high performance unsupervised feature selection method based on FME.

  • Hua Wang, Feiping Nie, Heng Huang. Learning Instance Specific Distance for Multi-Instance Classifications. The 25th AAAI Conference on Artificial Intelligence (AAAI), San Francisco, 2011.  (Acceptance Rate: 242/975=24.8%).

    Propose a very simple method to minimize the Lp norm function.

  • Yi Yang, Heng Tao Shen, Feiping Nie, Rongrong Ji, Xiaofang Zhou. Nonnegative Spectral Clustering with Discriminative Regularization. The 25th AAAI Conference on Artificial Intelligence (AAAI), San Francisco, 2011.  (Oral+Poster Acceptance Rate: 4.4%).  

    non-negative.zip

    AAAI11 Nonnegative Spectral Clustering with Discriminative Regularization.pdf

    A new nonnegative constrained approach is proposed for spectral clustering.

  • Xiao Cai, Feiping Nie, Heng Huang, Farhad Kamangar. Heterogeneous Image Features Integration via Multi-View Spectral Clustering. The 24th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Bellevue, 2011.  

    MVSpectralClustering.m

    CVPR11 Heterogeneous image feature integration via multi-modal spectral clustering.pdf

    A multi-view spectral clustering method is proposed to utilize different image features for clustering.

  • Yang Yang, Yi Yang, Zi Huang, Heng Tao Shen, Feiping Nie. Tag Localization with Spatial Correlations and Joint Group Sparsity. The 24th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Bellevue, 2011.

  • Feiping Nie, Hua Wang, Heng Huang, Chris Ding.  Unsupervised and Semi-supervised Learning via L1-norm Graph. The 13th International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011.  

    L1graph.zip

    ICCV11 unsupervised and semi-supervised learning via L1-norm graph.pdf

    A novel and interesting formulation for the Laplacian embedding. Benefit from L1 norm minimization, most of the differences ||f_i-f_j|| are zero, such that the embedding has clear clustering structure.

  • Hua Wang, Feiping Nie, Heng Huang, Shannon L. Risacher, Andrew J. Saykin, Li Shen, ADNI. Sparse Multi-Task Regression and Feature Selection to Identify Brain Imaging Predictors for Memory Performance. The 13th International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011.  

    L2R1R21.m

  • Hua Wang, Feiping Nie, Heng Huang, Chris Ding.  Transfer Dyadic Knowledge for Cross-Domain Image Classification. The 13th International Conference on Computer Vision (ICCV), Barcelona, Spain, 2011.

    A NMTF based method is proposed for transfer (multi-domain) learning.

  • Hua Wang, Heng Huang, Feiping Nie, Chris Ding.  Cross-Language Web Page Classification via Dual Knowledge Transfer Using Nonnegative Matrix Tri-Factorization. The 34th Annual ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), Beijing, 2011.  (Regular paper, 108/545=19.8%)

  • Zhigang Ma, Yi Yang, Feiping Nie, Jasper Uijlings, Nicu Sebe.  Exploiting the Entire Feature Space with Sparsity for Automatic Image Annotation. ACM International Conference on Multimedia (ACM MM), Scottsdale, USA, 2011. (Full paper, 17%)

    semisupervised_feature_slection.zip

    A high performance semi-supervised feature selection method based on FME.

  • Dijun Luo, Chris Ding, Heng Huang, Feiping Nie. Consensus Spectral Clustering in Near-Linear Time. The IEEE International Conference on Data Engineering (ICDE), Hannover, 2011.  (Acceptance Rate: 98/494=19.8%)

    ICDE11 Consensus Spectral Clustering in Near-Linear Time.pdf

    An O(nlogn) algorithm for spectral clustering, which can be used for large scale clustering.

  • Hua Wang, Feiping Nie, Heng Huang, Shannon Risacher, Andrew J Saykin, Li Shen, ADNI. Identifying AD-Sensitive and Cognition-Relevant Imaging Biomarkers via Joint Classification and Regression. The 14th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Toronto, 2011.  (Oral paper. Acceptance Rate: 34/819=4.2%).  

    LogisticL2RegressionR1R21_different.m

  • Dijun Luo, Feiping Nie, Chris Ding, Heng Huang. Multi-Subspace Discovery and Representation. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Athens, Greece, 2011.  (Acceptance Rate: 121/599=20.2%).   Best Student Paper Runner-up Award

    ECML PKDD11 Multi-Subspace Representation and Discovery.pdf

  • Hua Wang, Feiping Nie, Heng Huang, and Chris Ding.  Nonnegative Matrix Tri-Factorization Based High-Order Co-Clustering and Its Fast Implementation. IEEE International Conference on Data Mining (ICDM), Vancouver, Canada, 2011. (Full paper, 101/806=12.5%)

  • Xiao Cai, Feiping Nie, Heng Huang, and Chris Ding.  Multi-Class L2,1-Norms Support Vector Machine. IEEE International Conference on Data Mining (ICDM), Vancouver, Canada, 2011.  (Full paper, 101/806=12.5%)

    SVM21norm.zip

    A convex feature selection method based on multi-class SVM.

2010

  • Shiming Xiang, Feiping Nie, and Changshui Zhang. Semi-Supervised Classification via Local Spline Regression. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 32, no. 11, pp.2039-2053, 2010.  

    semi_pami10.rar

    TPAMI10 Semi-Supervised Classification via Local Spline Regression.pdf

    A graph construction approach via local spline regression is proposed for semi-supervised learning, which behaves excellent performance in the image segmentation and image matting tasks. Strictly prove the Laplacian matrices computed by LLE and Local Learning are exactly the same.

  • Feiping Nie, Dong Xu, Ivor W. Tsang, Changshui Zhang. Flexible Manifold Embedding: A Framework for Semi-supervised and Unsupervised Dimension Reduction. IEEE Transactions on Image Processing (TIP), 19(7):1921-1932, 2010.

    FME.zip

    TIP10 Flexible Manifold Embedding A Framework for Semi-supervised and Unsupervised Dimension Reduction.pdf

    A general framework (more general than the graph embedding framework) for dimensionality reduction from which new method can achieve better performance. Interestingly, two well studied linearizations (LPP like and SR like) are two extreme cases of the framework (ur->inf and ur->0).

  • Yi Yang, Dong Xu, Feiping Nie, Shuicheng Yan, Yueting Zhuang. Image Clustering using Local Discriminant Models and Global Integration. IEEE Transactions on Image Processing (TIP), 19(10):2761-2773, 2010.  

    LDMGI.rar

  • Shiming Xiang, Chunhong Pan, Feiping Nie, and Changshui Zhang. TurboPixel Segmentation Using  Eigen-Images. IEEE Transactions on Image Processing (TIP). 19(11):3024-3034, 2010.

    Superpixel for image segmentation.

  • Dijun Luo, Heng Huang, Chris Ding, Feiping Nie. On The Eigenvectors of p-Laplacian. Machine Learning (ML), 81(1):37-51, 2010.

    ML10 On The Eigenvectors of p-Laplacian.pdf

    An algorithm to find all the eigenvectors of p-Laplacian.

  • Chenping Hou, Changshui Zhang, Yi Wu, Feiping Nie. Multiple View Semi-Supervised Dimensionality Reduction. Pattern Recognition (PR), Volume 43, Issue 3, Pages 720-730, 2010.  

    MVSSDR.rar

  • Changshui Zhang, Feiping Nie*, Shiming Xiang. A General Kernelization Framework for Learning Algorithms Based on Kernel PCA. Neurocomputing, 2010, 73(4-6): 959-967.  

    GeneralKernelization.zip

    NCI10 A General Kernelization Framework for Learning Algorithms Based on Kernel PCA.pdf

    Almost all the linear methods could be easily kernelized via performing the linear method with transformed data by KPCA. Benefiting from this general kernelization framework, it is not necessary to derive the kernel version for each specific linear method.

  • Feiping Nie, Shiming Xiang, Yun Liu, Changshui Zhang. A General Graph-Based Semi-Supervised Learning with Novel Class Discovery. Neural Computing Applications (NCA), 2010, 19(4): 549-555.  

    GeneralSSL.m

    NCA10 A General Graph-Based Semi-Supervised Learning with Novel Class Discovery.pdf

    A general label propagation is proposed, and analyze how to make it has the following abilities: remove label noise, discover new class, perform ranking (learn with only positive labels).

  • Feiping Nie, Heng Huang, Xiao Cai, Chris Ding. Efficient and Robust Feature Selection via Joint L21-Norms Minimization. Advances in Neural Information Processing Systems 23 (NIPS), 2010.  (Acceptance Rate: 293/1219=24.0%).  

    CODE   gene expression data.rar

    NIPS10 Efficient and Robust Feature Selection via Joint L21-Norms Minimization.pdf

    The proposed re-weighted method is very easy to implement, and can be used to solve very general problem. For example, it can be used to minimize almost all the existing robust loss functions!

  • Yi Yang, Feiping Nie, Shiming Xiang, Yueting Zhuang, Wenhua Wang. Local and Global Regressive Mapping for Manifold Learning with Out-of-Sample Extrapolation. The 24rd AAAI Conference on Artificial Intelligence (AAAI), Atlanta, 2010.  (Oral paper, Acceptance Rate: 264/982=26.9%).  

    lgrm.rar

    FME with kernel regression for manifold learning (nonlinear dimensionality reduction), which can natually solve the out-of-sample issue in manifold learning.

  • Feiping Nie, Chris Ding, Dijun Luo, Heng Huang. Improved MinMax Cut Graph Clustering with Nonnegative Relaxation. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Barcelona, 2010.  (Oral paper, Acceptance Rate: 120/658=18.2%).

    mmc_nonnegative.m

    ECML PKDD10 Improved MinMax Cut Graph Clustering with Nonnegative Relaxation.pdf

    In addition to spectral relaxation, the nonnegative relaxation is proposed for clustering, which is a much tighter relaxation and the resulted solution is discrete and can be directly used for assigning cluster labels.

  • Yun Liu, Feiping Nie, Jigang Wu, Lihui Chen. Semi-supervised Feature Selection Based on Label Propagation and Subset Selection. The International Conference on Computer and Information Application (ICCIA), Tianjin, 2010.  (Oral paper).

    semiTRCFS.m

2009

  • Shiming Xiang, Feiping Nie, Chunxia Zhang and Changshui Zhang. Interactive Natural Image Segmentation via Spline Regression. IEEE Transactions on Image Processing (TIP), Volume 18, Issue 7, Pages1623-1632, 2009.  

    interactive_image_segmentation_for_web.zip

  • Yangqing Jia, Feiping Nie, Changshui Zhang. Trace Ratio Problem Revisited. IEEE Transactions on Neural Networks (TNN), Volume 20, Issue 4, Pages 729-735, 2009.  

    TraceRatio.rar

    TNN09 Trace Ratio Problem Revisited.pdf

    Trace ratio is an important criterion in dimensionality reduction and multi-objective optimization since it is parameter free. A fast algorithm is proposed and theoretical anlysis show its convergence rate is quadratic.

  • Shiming Xiang, Feiping Nie, Changshui Zhang and Chunxia Zhang. Nonlinear Dimensionality Reduction with Local Spline Embedding. IEEE Transactions on Knowledge and Data Engineering(TKDE), Volume 21, Issue 9, Pages 1285-1298, 2009.  

    LSE_code.rar

    TKDE09 Nonlinear Dimensionality Reduction with Local Spline Embedding.pdf

    Journal extension of ECML'06 with detailed algorithm, further analysis and more experiments.

  • Feiping Nie, Shiming Xiang, Yangqing Jia, Changshui Zhang. Semi-Supervised Orthogonal Discriminant Analysis via Label Propagation. Pattern Recognition (PR), Volume 42, Issue 11, Pages 2615-2627, 2009.  

    SODA.zip

    PR09 Semi-Supervised Orthogonal Discriminant Analysis via Label Propagation.pdf

    The scatter matrices Sw and Sb with probabilistic (soft) labels are proposed for semi-supervised LDA.

  • Feiping Nie, Shiming Xiang, Yangqiu Song, Changshui Zhang. Extracting the Optimal Dimensionality for Local Tensor Discriminant Analysis. Pattern Recognition (PR), Volume 42, Issue 1, Pages 105-114, 2009.

    LTDA.zip

    PR09 Extracting the Optimal Dimensionality for Local Tensor Discriminant Analysis.pdf

    In tensor subspace learning, k-order tensor needs k projection matrices. Therefore, how to automatically determine the optimal dimensionalities of the projection matrices becomes an important issue.

  • Shiming Xiang, Feiping Nie, Yangqiu Song, Changshui Zhang and Chunxia Zhang, Embedding New Data Points for Manifold Learning via Coordinate Propagation. Knowledge and Information Systems (KAIS) journal, Volume 19, Issue 2, Pages 159-184, 2009.

  • Feiping Nie, Shiming Xiang, Yangqiu Song and Changshui Zhang. Orthogonal Locality Minimizing Globality Maximizing Projections for Feature Extraction. Optical Engineering (OE),  Volume 18, Issue 1,  2009.

    LMGMP.zip

    OE09 Orthogonal Locality Minimizing Globality Maximizing Projections for Feature Extraction.pdf

    In LPP, the X*D*X' should be X*L_D*X', otherwise the data MUST be centerized before using LPP. The reason why X*D*X' was derived is analyized, and how to derive the correct X*L_D*X' is provided.

  • Feiping Nie, Dong Xu, Ivor W.Tsang, Changshui Zhang. Spectral Embedded Clustering. The 21st International Joint Conference on Artificial Intelligence (IJCAI), Pasadena, USA, 2009.  (Oral paper, Acceptance Rate: 25.7%).  

    SEC.m

    IJCAI09 Spectral Embedded Clustering.pdf

    A linearity regularization is proposed for spectral clustering in high dimensional case. Theoretical analysis shows that spectral clustering and its variants, K-means, discriminative K-means are all special cases of the new clustering method.

  • Yi Yang, Dong Xu, Feiping Nie, Jiebo Luo and Yueting Zhuang. Ranking with Local Regression and Global Alignment for Cross Media Retrieval. ACM International Conference on Multimedia (ACM MM), Beijing, China, 2009. (Full paper, Acceptance Rate: 16%).  

    LRGA_ranking.m

    Learning a new Laplacian matrix with a novel local linear regression model, and use it to solve the cross media retrieval problem.

  • Mingjie Qian, Feiping Nie, Changshui Zhang. Efficient Multi-class Unlabeled Constrained Semi-supervised SVM. The 18th ACM Conference on Information and Knowledge Management (CIKM), 2009.  

    Coordinate_Descent_MCUCSVM.m

  • Mingjie Qian, Feiping Nie, Changshui Zhang. Probabilistic labeled Semi-supervised SVM. Workshop on Optimization Based Methods for Emerging Data Mining Problems in conjunction with IEEE International Conference on Data Mining (ICDM Workshop), Florida, 2009.  

    Coordinate_Descent_PLMCSVM.m

    How to learn the SVM classifier if the given class labels are probabilistic (soft) labels.

2008

  • Shiming Xiang, Feiping Nie, and Changshui Zhang. Learning a Mahalanobis distance metric for data clustering and classification.Pattern Recognition (PR), Volume 41, Issue 12, Pages 3600 - 3612, 2008.  

    MDL.zip

    PR08 Learning a Mahalanobis Distance Metric for Data Clustering and Classification.pdf

    Journal extension of IJCAI'07, and proposed an effective Mahalanobis distance metric learning method based on the trace ratio criterion.

  • Shiming Xiang, Feiping Nie, Yangqiu Song, and Changshui Zhang. Contour graph based human tracking and action sequence recognition. Pattern Recognition (PR), Volume 41, Issue 12, Pages 3653 - 3664, 2008.

  • Yangqiu Song, Feiping Nie, Changshui Zhang, Shiming Xiang. A Unified Framework for Semi-Supervised Dimensionality Reduction. Pattern Recognition (PR), Volume 41, Issue 9, Pages 2789-2799, 2008.

    Independently proposed the Semi-superivsed Discriminant Analysis (SDA) and its many variants.

  • Feiping Nie, Shiming Xiang, Yangqing Jia, Changshui  Zhang, Shuicheng Yan. Trace Ratio Criterion for Feature Selection. The Twenty-Third AAAI Conference on Artificial Intelligence (AAAI), Chicago, 2008. oral paper.  

    TRCcode.zip

    AAAI08 Trace Ratio Criterion for Feature Selection.pdf

    An efficient algorithm to find the globally optimal solution to the subset selection problem with trace ratio criterion.

2007

  • Feiping Nie, Shiming Xiang, Changshui Zhang. Neighborhood MinMax Projections. The Twentieth International Joint Conference on Artificial Intelligence (IJCAI), Hyderabad, India, 2007.  (Oral paper, Acceptance Rate: 15.8%).  

    NMMP_ijcai.m

    IJCAI07 Neighborhood MinMax Projections.pdf

    An idea of local scatter matrices is proposed for discriminant analysis. The trace ratio problem is studied and show an iteresting property: larger dimension, smaller optimal objective value.

  • Shiming Xiang, Feiping Nie, Yangqiu Song, Changshui Zhang, and Chunxia Zhang. Embedding New Data Points for Manifold Learning via Coordinate Propagation. 11th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), 2007. (Oral paper, Acceptance Rate: 4.67%).   Best paper award honorable mention

  • Feiping Nie, Shiming Xiang, Yangqiu Song, Changshui Zhang. Optimal Dimensionality Discriminant Analysis and Its Application to Image Recognition. 1st Workshop on Component Analysis Methods for Classification, Clustering, Modeling and Estimation Problems in Computer Vision (CVPR workshop). 2007.  

    ODDA_cvpr.m

  • Feiping Nie, Shiming Xiang, Yangqiu Song, Changshui Zhang.  Extracting the Optimal Dimensionality for Discriminant Analysis. The 32nd International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hawaii, USA, 2007.  

    ODLDA_icassp.m

2006

  • Shiming Xiang, Feiping Nie, Changshui Zhang and Chunxia Zhang. Spline Embedding for Nonlinear Dimensionality Reduction.European Conference on Machine Learning (ECML), Berlin, Germany, 2006. LNAI 4212, pp. 825-832.  

    LSE_code.rar

    Local Spline Embedding (LSE) is proposed for manifold learning, which has better performance than LLE, LE and ISOMAP.








Locations of Site Visitors  

Scholars

Recently Visited

Similar Subject

Same institution

Similar Interests