解决隐含关联下的表征解耦，提升属性预测鲁棒性。
Coordinated Disentanglement with Iterative Mode Discovery Under Hidden Correlations
- 联合发现隐藏模式并强制条件独立，实现解耦学习。
- 在多种任务上达到当前最优性能，显著优于基线方法。
- 适合需要处理复杂数据关联的表示学习研究者。
解耦表征学习是实现鲁棒属性预测的强大范式。尽管近期方法已关注属性间的相关性，但隐藏相关性仍鲜受关注——即在某一属性取值下，数据中存在与其他属性相关的潜在模式。为保留模式信息并实现解耦，我们联合发现模式并施加基于模式的条件独立性。然而，这两个模块之间的相互依赖可能导致在简单迭代下误差放大。为此，我们提出协同解耦与迭代模式发现（CoDID）框架，包含动态架构以适应不断变化的模式数量，以及通过元优化缓解误差放大的协调机制。实证结果表明，该方法在多样任务上均表现优异，达到当前最优水平。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。