arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.01749cs.LGcs.AI
收藏

表示与标签的不变相关性:在噪声环境中增强域泛化

Invariant Correlation of Representation with Label: Enhancing Domain Generalization in Noisy Environments

Chinese Academy of Sciences(中国科学院);University of Liverpool(利物浦大学);Southeast University(东南大学)

Gaojie Jin, Ronghui Mu, Xinping Yi, Xiaowei Huang, Lijun Zhang

AI总结:

针对噪声环境中IRM相关方法因优化方向错误无法获得最优解的问题,提出ICorr方法,从因果视角证明其不变相关性是最优不变预测器的必要条件,并通过实验验证其在噪声数据集上的域泛化有效性。

摘要:

不变风险最小化(IRM)方法旨在通过训练在多个环境中保持不变的特征表示来应对域泛化挑战。然而,在噪声环境中,IRM相关技术(如IRMv1和VREx)可能无法获得最优IRM解,主要原因是优化方向错误。为解决该问题,我们提出ICorr(Invariant Correlation的缩写),一种旨在克服噪声环境中上述挑战的新方法。此外,我们通过案例研究分析为何先前方法可能失效而ICorr能成功。从理论角度(尤其因果视角),我们证明表示与标签的不变相关性是噪声环境中最优不变预测器的必要条件,而其他方法的优化动机则不然。我们还通过在多个噪声数据集上与其他域泛化方法对比,实证验证了ICorr的有效性。代码可在https://github.com/Alexkael/ICorr获取。

英文摘要:

The Invariant Risk Minimization (IRM) approach aims to address the challenge of domain generalization by training a feature representation that remains invariant across multiple environments. However, in noisy environments, IRM-related techniques such as IRMv1 and VREx may be unable to achieve the optimal IRM solution, primarily due to erroneous optimization directions. To address this issue, we introduce ICorr (an abbreviation for Invariant Correlation), a novel approach designed to surmount the above challenge in noisy settings. Additionally, we dig into a case study to analyze why previous methods may lose ground while ICorr can succeed. Through a theoretical lens, particularly from a causality perspective, we illustrate that the invariant correlation of representation with label is a necessary condition for the optimal invariant predictor in noisy environments, whereas the optimization motivations for other methods may not be. Furthermore, we empirically demonstrate the effectiveness of ICorr by comparing it with other domain generalization methods on various noisy datasets. The code is available at https://github.com/Alexkael/ICorr.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑