mlsanityData to 7 Oct 2026

Deep Generalized Canonical Correlation Analysis

arXiv 1702.02519 ↗First posted 8 Feb 2017cs.LG cs.AI stat.MLcited by 32

Not on the map. Why?

Abstract (arXiv)

We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a method for learning nonlinear transformations of arbitrarily many views of data, such that the resulting transformations are maximally informative of each other. While methods for nonlinear two-view representation learning (Deep CCA, (Andrew et al., 2013)) and linear many-view representation learning (Generalized CCA (Horst, 1961)) exist, DGCCA is the first CCA-style multiview representation learning technique that combines the flexibility of nonlinear (deep) representation learning with the statistical power of incorporating information from many independent sources, or views. We present the DGCCA formulation as well as an efficient stochastic optimization algorithm for solving it. We learn DGCCA representations on two distinct datasets for three downstream tasks: phonetic transcription from acoustic and articulatory measurements, and recommending hashtags and friends on a dataset of Twitter users. We find that DGCCA representations soundly beat existing methods at phonetic transcription and hashtag recommendation, and in general perform no worse than standard linear many-view techniques.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 9; 2024: 3; 2025: 9; 2026: 4.

32 papers.

Sort:

By area:

  1. 2023Multi-View Causal Representation Learning with Partial Observabilitycited by 72
  2. 2023Understanding Multimodal Contrastive Learning and Incorporating Unpaired Datacited by 43
  3. 2021Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspectivecited by 37
  4. 2023Deep Variational Multivariate Information Bottleneck -- A Framework for Variational Lossescited by 6
  5. 2023Revisiting Deep Generalized Canonical Correlation Analysiscited by 6
  6. 2025From Classical Machine Learning to Emerging Foundation Models: Review on Multimodal Data Integration for Cancer Researchcited by 6
  7. 2021Deep IDA: A Deep Learning Method for Integrative Discriminant Analysis of Multi-View Data with Feature Ranking -- An Application to COVID-19 severitycited by 5
  8. 2023Interpretable Deep Learning Methods for Multiview Learningcited by 5
  9. 2022SDGCCA: Supervised Deep Generalized Canonical Correlation Analysis for Multi-omics Integrationcited by 3
  10. 2023Scalable Randomized Kernel Methods for Multiview Data Integration and Predictioncited by 2
  11. 2023A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractorscited by 2
  12. 2025Multimodal Data Storage and Retrieval for Embodied AI: A Surveycited by 2
20 more
  1. 2025Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Surveycited by 2
  2. 2023Learning Representations without Compositional Assumptionscited by 1
  3. 2024Self Supervised Correlation-based Permutations for Multi-View Clusteringcited by 1
  4. 2024Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularizationcited by 1
  5. 2025Nonlinear Sparse Generalized Canonical Correlation Analysis for Multi-view High-dimensional Datacited by 1
  6. 2025Provable Affine Identifiability of Nonlinear CCA under Latent Distributional Priorscited by 1
  7. 2025Advanced Unsupervised Learning: A Comprehensive Overview of Multi-View Clustering Techniquescited by 1
  8. 2026Time Series, Vision, and Language: Exploring the Limits of Alignment in Contrastive Representation Spacescited by 1
  9. 2021Multi-view Deep One-class Classification: A Systematic Explorationcited by 0
  10. 2021Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation Analysiscited by 0
  11. 2022Deep Multi-View Semi-Supervised Clustering with Sample Pairwise Constraintscited by 0
  12. 2022How do Cross-View and Cross-Modal Alignment Affect Representations in Contrastive Learning?cited by 0
  13. 2023A deep learning pipeline for cross-sectional and longitudinal multiview data integrationcited by 0
  14. 2024Brain-Cognition Fingerprinting via Graph-GCCA with Contrastive Learningcited by 0
  15. 2025Generalized probabilistic canonical correlation analysis for multi-modal data integration with full or partial observationscited by 0
  16. 2025Generative Flexible Latent Structure Regression (GFLSR) modelcited by 0
  17. 2025CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalitiescited by 0
  18. 2026Emergent Structured Representations Support Flexible In-Context Inference in Large Language Modelscited by 0
  19. 2026Representation Selection via Cross-Model Agreement using Canonical Correlation Analysiscited by 0
  20. 2026Supervised Deep Multimodal Matrix Factorization for Interpretable Brain Network Analysiscited by 0