mlsanityData to 7 Oct 2026

Reconsidering Representation Alignment for Multi-view Clustering

arXiv 2103.07738 ↗First posted 13 Mar 2021cs.CV cs.LGcited by 57

Not on the map. Why?

Abstract (arXiv)

Aligning distributions of view representations is a core component of today's state of the art models for deep multi-view clustering. However, we identify several drawbacks with na"ively aligning representation distributions. We demonstrate that these drawbacks both lead to less separable clusters in the representation space, and inhibit the model's ability to prioritize views. Based on these observations, we develop a simple baseline model for deep multi-view clustering. Our baseline model avoids representation alignment altogether, while performing similar to, or better than, the current state of the art. We also expand our baseline model by adding a contrastive learning component. This introduces a selective alignment procedure that preserves the model's ability to prioritize views. Our experiments show that the contrastive learning component enhances the baseline model, improving on the current state of the art by a large margin on several datasets.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). Builds on 20 of its 66 references that are in the map. First posted on arXiv 13 Mar 2021.

Builds on

20 of 66 references.

References · 20

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  8. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  9. 2017Multimodal Machine Learning: A Survey and Taxonomycited by 1,004
  10. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  11. 2019Learning Representations by Maximizing Mutual Information Across Viewscited by 733
  12. 2016Coupled Generative Adversarial Networkscited by 216
8 more
  1. 2016On Deep Multi-View Representation Learning: Objectives and Optimizationcited by 162
  2. 2019Putting An End to End-to-End: Gradient-Isolated Learning of Representationscited by 85
  3. 2019MFAS: Multimodal Fusion Architecture Searchcited by 84
  4. 2019Domain Adaptation with Asymmetrically-Relaxed Distribution Alignmentcited by 61
  5. 2019On Learning Invariant Representation for Domain Adaptationcited by 38
  6. 2018Deep Multimodal Subspace Clustering Networkscited by 31
  7. 2019Deep Divergence-Based Approach to Clusteringcited by 13
  8. 2017XFlow: Cross-modal Deep Neural Networks for Audiovisual Classificationcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 16; 2024: 10; 2025: 17; 2026: 2.

57 papers.

Sort:

  1. 2021Multi-level Feature Learning for Contrastive Multi-view Clusteringcited by 73
  2. 2021This looks more like that: Enhancing Self-Explaining Models by Prototypical Relevance Propagationcited by 43
  3. 2021Self-Supervised Discriminative Feature Learning for Deep Multi-View Clusteringcited by 41
  4. 2023Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignmentcited by 33
  5. 2023GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clusteringcited by 30
  6. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  7. 2023Decoupled Contrastive Multi-View Clustering with High-Order Random Walkscited by 23
  8. 2022Contrastive Multi-view Hyperbolic Hierarchical Clusteringcited by 19
  9. 2023Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarioscited by 19
  10. 2023DealMVC: Dual Contrastive Calibration for Multi-view Clusteringcited by 19
  11. 2022Self-Supervised Information Bottleneck for Deep Multi-View Subspace Clusteringcited by 15
  12. 2023Incomplete Contrastive Multi-View Clustering with High-Confidence Guidingcited by 15
38 more
  1. 2024CDC: A Simple Framework for Complex Data Clusteringcited by 15
  2. 2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspectivecited by 14
  3. 2023Reliable Representation Learning for Incomplete Multi-View Missing Multi-Label Classificationcited by 12
  4. 2023On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clusteringcited by 10
  5. 2025Distributional Vision-Language Alignment by Cauchy-Schwarz Divergencecited by 7
  6. 2022A Clustering-guided Contrastive Fusion for Multi-view Representation Learningcited by 6
  7. 2022Multi-view Information Bottleneck Without Variational Approximationcited by 5
  8. 2023Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Trainingcited by 5
  9. 2023Joint Projection Learning and Tensor Decomposition Based Incomplete Multi-view Clusteringcited by 5
  10. 2024Rethinking Multi-view Representation Learning via Distilled Disentanglingcited by 5
  11. 2022MORI-RAN: Multi-view Robust Representation Learning via Hybrid Contrastive Fusioncited by 4
  12. 2022Subspace-Contrastive Multi-View Clusteringcited by 4
  13. 2023Disentangling Multi-view Representations Beyond Inductive Biascited by 4
  14. 2022Information Maximization for Extreme Pose Face Recognitioncited by 3
  15. 2023Asymmetric double-winged multi-view clustering network for exploring Diverse and Consistent Informationcited by 3
  16. 2025Robust Multi-View Learning via Representation Fusion of Sample-Level Attention and Alignment of Simulated Perturbationcited by 3
  17. 2025InfoMAE: Pair-Efficient Cross-Modal Alignment for Multimodal Time-Series Sensing Signalscited by 3
  18. 2025Automatically Identify and Rectify: Robust Deep Contrastive Multi-view Clustering in Noisy Scenarioscited by 3
  19. 2023Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination Methodscited by 2
  20. 2025Towards Learnable Anchor for Deep Multi-View Clusteringcited by 2
  21. 2025PROTOCOL: Partial Optimal Transport-enhanced Contrastive Learning for Imbalanced Multi-view Clusteringcited by 2
  22. 2026Learning Disentangled Representations for Generalized Multi-view Clusteringcited by 2
  23. 2022Explicit View-labels Matter: A Multifacet Complementarity Study of Multi-view Clusteringcited by 1
  24. 2023MoCLIM: Towards Accurate Cancer Subtyping via Multi-Omics Contrastive Learning with Omics-Inference Modelingcited by 1
  25. 2023Self-supervised Multi-view Clustering in Computer Vision: A Surveycited by 1
  26. 2024Self Supervised Correlation-based Permutations for Multi-View Clusteringcited by 1
  27. 2024Deep Contrastive Multi-view Clustering under Semantic Feature Guidancecited by 1
  28. 2024Regularized Contrastive Partial Multi-view Outlier Detectioncited by 1
  29. 2024Task-Augmented Cross-View Imputation Network for Partial Multi-View Incomplete Multi-Label Classificationcited by 1
  30. 2024Generalizable and Robust Spectral Method for Multi-view Representation Learningcited by 1
  31. 2025Hierarchical Consensus Network for Multiview Feature Learningcited by 1
  32. 2025Adversarial Fair Multi-View Clusteringcited by 1
  33. 2025Generalized Deep Multi-view Clustering via Causal Learning with Partially Aligned Cross-view Correspondencecited by 1
  34. 2022How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?cited by 0
  35. 2024Consistency Enhancement-Based Deep Multiview Clustering via Contrastive Learningcited by 0
  36. 2024Generalized Cauchy-Schwarz Divergence and Its Deep Learning Applicationscited by 0
  37. 2025Multi-view Clustering via Bi-level Decoupling and Consistency Learningcited by 0
  38. 2025Generative Diffusion Contrastive Network for Multi-View Clusteringcited by 0

50 most cited of 57 All 57 (JSON)