# Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations

arXiv: https://arxiv.org/abs/2607.17264 · HTML: https://mlsanity.com/paper/2607.17264/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 59 references that are in the map.
- First posted on arXiv 19 Jul 2026.

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Out-of-Distribution Generalization via Risk Extrapolation (REx)](https://mlsanity.com/paper/2003.00688/) (2020)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustness](https://mlsanity.com/paper/1811.00007/) (2018)
- [Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observations](https://mlsanity.com/paper/1705.08841/) (2017)
- [On Disentangled Representations Learned From Correlated Data](https://mlsanity.com/paper/2006.07886/) (2020)
- [Desiderata for Representation Learning: A Causal Perspective](https://mlsanity.com/paper/2109.03795/) (2021)
- [On the Transfer of Disentangled Representations in Realistic Settings](https://mlsanity.com/paper/2010.14407/) (2020)
- [Using latent space regression to analyze and leverage compositionality in GANs](https://mlsanity.com/paper/2103.10426/) (2021)
- [DeepDPM: Deep Clustering With an Unknown Number of Clusters](https://mlsanity.com/paper/2203.14309/) (2022)
- [Disentanglement of Correlated Factors via Hausdorff Factorized Support](https://mlsanity.com/paper/2210.07347/) (2022)
- [Improving Zero-shot Voice Style Transfer via Disentangled Representation Learning](https://mlsanity.com/paper/2103.09420/) (2021)
- [Conditional Mutual Information for Disentangled Representations in Reinforcement Learning](https://mlsanity.com/paper/2305.14133/) (2023)
- [Multi-Domain Adversarial Feature Generalization for Person Re-Identification](https://mlsanity.com/paper/2011.12563/) (2020)
- [Learning Disentangled Representations for Counterfactual Regression via Mutual Information Minimization](https://mlsanity.com/paper/2206.01022/) (2022)
- [Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric](https://mlsanity.com/paper/2209.12396/) (2022)
- [Learning a Unified Sample Weighting Network for Object Detection](https://mlsanity.com/paper/2006.06568/) (2020)
- [Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models](https://mlsanity.com/paper/2407.18999/) (2024)
- [Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition](https://mlsanity.com/paper/2202.07260/) (2022)

## 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.