聚合数据掩盖了分布外泛化失败，真实存在性能倒挂现象
Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations
- 用梯度方法识别出语义一致的分布外子集
- 发现一半以上子集中高内分布准确率对应低分布外准确率
- 提醒研究者警惕平均指标误导，适合关注模型鲁棒性的学者
分布外（OOD）泛化评估常显示模型在内分布（ID）与分布外（OOD）上的准确率呈强正相关，称为“准确率在线”现象。这一现象常被解读为虚假相关性（即提升内分布但降低分布外性能的关联）在实践中罕见。我们发现该正相关性往往源于对异质性分布外样本的聚合。通过一种简单的基于梯度的方法——OODSelect，我们识别出语义一致的分布外子集，在这些子集中，“准确率在线”关系不成立。在多个主流分布偏移基准上，发现部分子集占比超过一半，且更高内分布准确率反而预测更低的分布外准确率。结果表明，聚合指标可能掩盖分布外鲁棒性的关键失败模式。我们已开源代码及识别出的子集，以促进后续研究。
原文摘要 · Abstract (English)
Benchmarks for out-of-distribution (OOD) generalization frequently show a strong positive correlation between in-distribution (ID) and OOD accuracy across models, termed "accuracy-on-the-line." This pattern is often taken to imply that spurious correlations - correlations that improve ID but reduce OOD performance - are rare in practice. We find that this positive correlation is often an artifact of aggregating heterogeneous OOD examples. Using a simple gradient-based method, OODSelect, we identify semantically coherent OOD subsets where accuracy on the line does not hold. Across widely used distribution shift benchmarks, the OODSelect uncovers subsets, sometimes over half of the standard OOD set, where higher ID accuracy predicts lower OOD accuracy. Our findings indicate that aggregate metrics can obscure important failure modes of OOD robustness. We release code and the identified subsets to facilitate further research.
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。