mlsanityData to 7 Oct 2026

Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations

arXiv 2607.17264 ↗First posted 19 Jul 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Disentangled representation learning is a powerful paradigm for robust attribute prediction. While recent methods address attribute correlations, hidden correlations remain underexplored, where data under the value of a certain attribute exhibit underlying modes correlated with other attributes. To preserve mode information and achieve disentanglement, we jointly discover modes and enforce mode-based conditional independence. Yet, the interdependency between these two modules may lead to error amplification under naive iterations. We propose Coordinated Disentanglement with Iterative mode Discovery (CoDID), an end-to-end framework featuring a dynamic architecture that adapts to evolving number of modes, and a coordination mechanism that mitigates error amplification via meta-optimization. Empirical results demonstrate the state-of-the-art performance on diverse tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 19 Jul 2026.

Builds on

33 of 59 references.

References · 33

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023Segment Anythingcited by 8,158
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  8. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  9. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  10. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  11. 2018MINE: Mutual Information Neural Estimationcited by 680
  12. 2018Disentangling by Factorisingcited by 614
21 more
  1. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  2. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  3. 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
  4. 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
  5. 2020On Disentangled Representations Learned From Correlated Datacited by 94
  6. 2021Desiderata for Representation Learning: A Causal Perspectivecited by 76
  7. 2020On the Transfer of Disentangled Representations in Realistic Settingscited by 63
  8. 2021Using latent space regression to analyze and leverage compositionality in GANscited by 55
  9. 2022DeepDPM: Deep Clustering With an Unknown Number of Clusterscited by 52
  10. 2022Disentanglement of Correlated Factors via Hausdorff Factorized Supportcited by 37
  11. 2021Improving Zero-shot Voice Style Transfer via Disentangled Representation Learningcited by 32
  12. 2023Conditional Mutual Information for Disentangled Representations in Reinforcement Learningcited by 27
  13. 2020Multi-Domain Adversarial Feature Generalization for Person Re-Identificationcited by 22
  14. 2022Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimizationcited by 18
  15. 2022Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metriccited by 17
  16. 2020Learning a Unified Sample Weighting Network for Object Detectioncited by 10
  17. 2022Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognitioncited by 9
  18. 2024Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Modelscited by 9
  19. 2021Disentanglement and Generalization Under Correlation Shiftscited by 8
  20. 2024Seeing Your Speech Style: A Novel Zero-Shot Identity-Disentanglement Face-based Voice Conversioncited by 3
  21. 2025ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecastingcited by 2

Built on by

Not cited yet.