AI 中文总结
研究针对解缠表示学习中隐藏相关性未充分探索的问题，提出CoDID框架，通过动态架构适应模式数量变化，利用协调机制减轻误差放大以实现协同解缠，在多样任务上展现最优性能。
AI 中文摘要
解缠表示学习是用于稳健属性预测的强大范式。近期方法处理了属性相关性，但隐藏相关性仍未得到充分探索，即某属性值下的数据呈现与其他属性相关的潜在模式。为保留模式信息并实现解缠，我们联合发现模式并强制基于模式的条件独立性。然而，这两个模块之间的相互依赖性在简单迭代下可能导致误差放大。我们提出了具有迭代模式发现的协同解缠（CoDID），这是一个端到端框架，具有适应不断变化的模式数量的动态架构，以及通过元优化减轻误差放大的协调机制。实证结果证明了在各种任务上的最优性能。
英文摘要
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.
CommentsPublished at ICML 2026
Journal refProceedings of the 43rd International Conference on Machine Learning, PMLR 306:44590-44622, 2026. https://proceedings.mlr.press/v306/hu26e.html
