Multi-view learning methods with code

Part A: general multi-view methods with code

1. NMF (non-negative matrix factorization) based methods

 NMF factorizes the non-negative data matrix into two non-negative matrices.

• 1.1 AAAI17 Multi-View Clustering via Deep Matrix Factorization (matlab)

  • Deep Matrix Factorization is a variant of NMF.

• 1.2 ICPR16 Partial Multi-View Clustering Using Graph Regularized NMF (matlab)

• 1.3 ICDM16 Multi-View Clustering via Concept Factorization with Local Manifold Regularization (matlab)

  • Concept Factorization is a variant of NMF.

• 1.4 TC19 Individuality- and Commonality-Based Multiview Multilabel Learning (matlab)

• 1.5 AAAI14 Partial Multi-View Clustering (matlab)

• 1.6 TNNLS15 Partially Shared Latent Factor Learning With Multiview Data (matlab)

• 1.7 S18 Multi-view Discriminative Learning via Joint Non-negative Matrix Factorization (matlab)

• 1.8 ICDM13 Multi-View Clustering via Joint Nonnegative Matrix Factorization (matlab)

• 1.9 KBS20 Multi-view clustering by non-negative matrix factorization with co-orthogonal constraints (matlab)

• 1.10 KBS20 Semi-supervised Multi-view Clustering with Graph-regularized Partially Shared Non-negative Matrix Factorization (matlab)

• 1.11 NC18 Adaptive Structure Concept Factorization for Multiview Clustering (matlab)

  • Concept Factorization is a variant of NMF.

• 1.12 ICDE20 A Novel Approach to Learning Consensus and Complementary Information for Multi-View Data Clustering (matlab)

• 1.13 ECCV20 SPL-MLL: Selecting Predictable Landmarks for Multi-Label Learning (python)

• 1.14 PR20 Auto-weighted Multi-view Clustering via Deep Matrix Decomposition (matlab)

2. Graph based methods

 It contains two kinds of methods. The first kind is using a predefined graph (also resfer to the traditional spectral clustering), and performing post-processing spectral clustering or k-means. And the second kind is to learn the graph and the index matrix simultaneously. 

• 2.1 ICDM19 Consistency Meets Inconsistency: A Unified Graph Learning Framework for Multi-view Clustering (matlab)

• 2.2 TIP19 Multiview Consensus Graph Clustering (matlab)

• 2.3 TIP18 Auto-Weighted Multi-View Learning for Image Clustering and Semi-Supervised Classification (matlab)(python)

  • The conference variant is AAAI17 Multi-View Clustering and Semi-Supervised Classification with Adaptive Neighbours.

• 2.4 TKDE19 GMC Graph-based Multi-view Clustering (matlab)

• 2.5 BD17 Multi-View Graph Learning with Adaptive Label Propagation (matlab)

• 2.6 TC18 Graph Learning for Multiview Clustering (matlab)

• 2.7 IJCAI16 Parameter-Free Auto-Weighted Multiple Graph Learning (matlab)

• 2.8 TC18 Incomplete Multiview Spectral Clustering With Adaptive Graph Learning (matlab)

• 2.9 TKDE19 Graph structure fusion for multiview clustering (matlab)

• 2.10 ACML19 Latent Multi-view Semi-Supervised Classification (matlab)

• 2.11 NN20 Partition level multiview subspace clustering (matlab)

• 2.12 KBS20 Multi-graph Fusion for Multi-view Spectral Clustering (matlab)

• 2.13 TIP17 Flexible Multi-view Dimensionality co-Reduction (matlab)

• 2.14 ICML19 COMIC: Multi-view Clustering Without Parameter Selection (python)

• 2.15 AAAI20 Multi-View Clustering in Latent Embedding Space (matlab)

• 2.16 PR19 Multi-view Subspace Clustering with Intactness-Aware Similarity (matlab)

• 2.17 IF20 Multi-view spectral clustering via integrating nonnegative embedding and spectral embedding (matlab)

• 2.18 N19 Auto-weighted multi-view constrained spectral clustering (matlab)

• 2.19 KBS19 A Study of Graph-based System for Multi-view Clustering (matlab)

• 2.20 PR19 Auto-weighted Multi-view Clustering via Kernelized Graph Learning (matlab)

• 2.21 TKDE21 Measuring Diversity in Graph Learning: A Unified Framework for Structured Multi-view Clustering (matlab)

• 2.22 IJCAI21 Graph Filter-based Multi-view Attributed Graph Clustering (python)

• 2.23 TCYB21 Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view (matlab)

• 2.24 TKDE20 Multi-View Spectral Clustering with High-Order Optimal Neighborhood Laplacian Matrix (matlab)

• 2.25 TKDE21 Consensus Graph Learning for Multi-view Clustering (matlab&python)

3. Self-representation based methods

 Self-representation means that each data sample is expressed by a linear combination of other samples in the same subspace.

• 3.1 AAAI18 Consistent and Specific Multi-View Subspace Clustering (matlab)

• 3.2 The method in 2.8 is also a self-representation based method.

• 3.3 PR18 Multi-view Low-rank Sparse Subspace Clustering (matlab)

• 3.4 CVPR15 Diversity-induced Multi-view Subspace Clustering (matlab)

• 3.5 TIP19 Split Multiplicative Multi-view Subspace Clustering (matlab)

• 3.6 CVPR17 Exclusivity-Consistency Regularized Multi-view Subspace Clustering (matlab)

• 3.7 TPAMI20 Generalized Latent Multi-view Subspace Clustering (matlab)

  • The conference variant is CVPR17 Latent Multi-view Subspace Clustering.

• 3.8 IS21 Multi-view Subspace Clustering via Partition Fusion (matlab)

• 3.9 TNNLS21 Multiview Subspace Clustering via Co-Training Robust Data Representation (matlab)

• 3.10 TKDE20 Consensus One-step Multi-view Subspace Clustering (matlab)

4. Tensor based methods

 The tensor is the generalization of the matrix concept. And the matrix case is a 2-order tensor.

• 4.1 TNNLS18 Multiview Subspace Clustering via Tensorial t-Product Representation (matlab)

• 4.2 ICCV15 Low-Rank Tensor Constrained Multiview Subspace Clustering (matlab)

• 4.3 TIP19 Essential tensor learning for multi-view spectral clustering (matlab)

• 4.4 IJCV20 Tensorized Multi-View Subspace Representation Learning (matlab)

  • The conference variant may be ICCV15 Low-Rank Tensor Constrained Multiview Subspace Clustering.

• 4.5 IJCV18 On Unifying Multi-view Self-Representations for Clustering by Tensor Multi-rank Minimization (matlab)

• 4.6 TCYB20 Hyper-Laplacian Regularized Multilinear Multi-View Self-Representation for Clustering and Semi-supervised Learning (matlab)

• 4.7 TCSVT21 Multi-View Spectral Clustering Tailored Tensor Low-Rank Representation (matlab)

• 4.8 TKDE20 TCCANet: Tensor Canonical Correlation Analysis Networks for Multi-view Remote Sensing Scene Recognition (matlab)

5. Kernel learning based methods

• 5.1 N18 Local kernel alignment based multi-view clustering using extreme learning machine (matlab)

• 5.2 TKDE20 Optimal Neighborhood Multiple Kernel Clustering with Adaptive Local Kernels (matlab)

6. Dictionary learning based methods

• 6.1 Access18 Multi-view Analysis Dictionary Learning for Image Classification (matlab)

• 6.2 TIP16 Multimodal Task-Driven Dictionary Learning for Image Classification(matlab)

7. Deep learning based or network based methods

   Part A 11 self-supervised learning (or contrastive learning) is also based on Deep learning.

• 7.1 TIP19 Multi-view Deep Subspace Clustering Networks (python)

• 7.2 NIPS19 CPM-Nets: Cross Partial Multi-View Networks (python)

• 7.3 AAA18 Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction (python)

• 7.4 TKDE20 MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation (python)

• 7.5 TIP19 Multi-View Linear Discriminant Analysis Network (python)

• 7.6 TIP19 Deep Multi-View Learning Using Neuron-Wise Correlation-Maximizing Regularizers (python)

• 7.7 ICCV15 Multi-view Convolutional Neural Networks for 3D Shape Recognition (matlab)

• 7.8 CVPR19 AE2-Nets:Autoencoder in Autoencoder Networks (python)

• 7.9 IJCAI19 Multi-view Spectral Clustering Network (python)

• 7.10 ICCV19 Reciprocal Multi-Layer Subspace Learning for Multi-View Clustering (matlab)

• 7.11 ICLR20 Learning Robust Representations via Multi-View Information Bottleneck (python)

• 7.12 SIAM19 Deep Multi-view Information Bottleneck (python)

8. SVM based methods

• 8.1 TNNLS18 Multiview Privileged Support Vector Machines (matlab)

• 8.2 KBS18 Multi-view learning based on Nonparallel Support Vector Machine (matlab)

• 8.3 IS19 Coupling Privileged Kernel Method for Multi-view Learning (matlab)

9. Co-training based methods

• 9.1 JMLR20 Self-paced Multi-view Co-training (python)

10. Metric Learning based methods

• 10.1 IJCAI18 FISH-MML: Fisher-HSIC Multi-View Metric Learning(matlab)

11. Self-supervised Learning based methods

• 11.1 ICLR21 Self-supervised Learning from a Multi-view Perspective (python)

• 11.2 ECCV20 Contrastive Multiview Coding (python)

• 11.3 ICML20 Contrastive Multi-View Representation Learning on Graphs (python)

Part B: multi-view applications with code

1. Incomplete or partial multi-view learning

 Some views of samples are missing.

• 1.1 AAAI19 Unified Embedding Alignment with Missing Views Inferring for Incomplete Multi-View Clustering (matlab)

• 1.2 ECML15 Multiple Incomplete Views Clustering via Weighted Nonnegative Matrix Factorization with L2,1 Regularization (matlab)

• 1.3 BD16 Online Multi-view Clustering with Incomplete Views (matlab)

• 1.4 IJCAI16 Incomplete Multi-Modal Visual Data Grouping (matlab)

• 1.5 TC20 Generalized Incomplete Multiview Clustering With Flexible Locality Structure Diffusion (matlab)

• 1.6 IJCAI19 Spectral Perturbation Meets Incomplete Multi-view Data (matlab)

• 1.7 TPAMI, in press, Deep Partial Multi-View Learning (python)

  • The conference variant is NIPS19 CPM-Nets: Cross Partial Multi-View Networks.

• 1.8 TPAMI20 Efficient and Effective Regularized Incomplete Multi-view Clustering (matlab)

• 1.9 TPAMI19 Late Fusion Incomplete Multi-view Clustering (matlab)

• 2.0 ICME21 Tensor-based Multi-view Block-diagonal Structure Diffusion for Clustering Incomplete Multi-view Data (matlab)

2. Person Re-Identification

• 2.1 TPAMI18 Person Re-Identification by Cross-View Multi-Level Dictionary Learning (matlab)

3. Outlier detection

• 3.1 TKDD18 Multi-View Low-Rank Analysis with Applications to Outlier Detection (matlab)

• 3.2 AAAI18 Partial Multi-View Outlier Detection (matlab)

4. Zero shot learning

• 4.1 ECCV14 Transductive Multi-view Embedding for Zero-Shot Recognition and Annotation (matlab)

5. Multi-label learning or Weak-label learning

• 5.1 SIAM SDM18 Multi-view Weak-label Learning based on Matrix Completion (matlab)

  • Weak-label learning is an important branch of multi-label learning.

• 5.2 Access19 Multi-View Multi-Label Learning With View-Label-Specific Features (matlab)

• 5.3 The method in 1.4 is also a multi-label learning method.

• 5.4 IJCAI18 Incomplete Multi-View Weak-Label Learning (matlab)

• 5.5 IJCAI20 Weakly-Supervised Multi-view Multi-instance Multi-label Learning (matlab)

6. Online learning

• 6.1 ICDM16 Online Unsupervised Multi-view Feature Selection (matlab)

7. Multi-Instance learning

• 7.1 AAA19 Multi-View Multi-Instance Multi-Label Learning based on Collaborative Matrix Factorization (matlab)

8. Large-scale clustering

• 8.1 AAAI20 Large-scale Multi-view Subspace Clustering in Linear Time (matlab)

• 8.2 AAAI15 Large-scale multi-view spectral clustering via bipartite graph (matlab)

9. Non-independently and Non-identically Distributed Complex Noise

• 9.1 TNNLS19 Robust Multi-view Subspace Learning with Non-independently and Non-identically Distributed Complex Noise (matlab)

10. Multiview training boost Single-view test

• 10.1 TPAMI20 Multiview Feature Selection for Single-view Classification (matlab)

11. Fuzzy clustering

• 11.1 PR21 Collaborative feature-weighted multi-view fuzzy c-means clustering (matlab)

Part C: Others

• 1.1 famous authors in the field of multi-view learning

  • Feiping Nie (Google Scholar Citations) (home)

• 1.2 other github pages with code