新方法同时解决环境间与样本内分布偏移，提升模型泛化能力。
Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization
- 基于环境条件重加权，联合优化环境间不变性与样本内鲁棒性
- 在混合分布偏移下，最差环境与平均OOD性能均显著提升
- 适用于无显式环境标注场景，通过极小极大框架推断潜在环境
当模型同时面临环境间的相关性偏移与由罕见或困难样本引发的多样性偏移时，分布外（OOD）泛化仍具挑战。现有不变风险最小化（IRM）方法主要处理环境层面的虚假相关性，常忽略环境中样本级异质性，这会严重影响OOD表现。本文提出环境条件尾部重加权的总变差不变学习（ECTR），将基于总变差的不变学习与环境条件尾部重加权相结合，统一应对两类分布偏移。通过整合环境级不变性与环境内鲁棒性，使两种机制在混合分布偏移下相互补充。我们进一步将框架扩展至无显式环境标注场景，通过极小极大公式推断潜在环境。在回归、表格、时间序列及图像分类基准上，面对混合分布偏移，该方法在最差环境和平均OOD性能上均实现持续提升。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) generalization remains challenging when models simultaneously encounter correlation shifts across environments and diversity shifts driven by rare or hard samples. Existing invariant risk minimization (IRM) methods primarily address spurious correlations at the environment level, but often overlook sample-level heterogeneity within environments, which can critically impact OOD performance. In this work, we propose Environment-Conditioned Tail Reweighting for Total Variation Invariant Risk Minimization (ECTR), a unified framework that augments TV-based invariant learning with environment-conditioned tail reweighting to jointly address both types of distribution shift. By integrating environment-level invariance with within-environment robustness, the proposed approach makes these two mechanisms complementary under mixed distribution shifts. We further extend the framework to scenarios without explicit environment annotations by inferring latent environments through a minimax formulation. Experiments across regression, tabular, time-series, and image classification benchmarks under mixed distribution shifts demonstrate consistent improvements in both worst-environment and average OOD performance.
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。