arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.18205cs.LGstat.ML
收藏

桥接OOD检测与泛化:图论视角

Bridging OOD Detection and Generalization: A Graph-Theoretic View

UIUC(伊利诺伊大学厄巴纳-香槟分校);UW-Madison(威斯康星大学麦迪逊分校)

Han Wang, Yixuan Li

AI总结:

针对真实场景中模型面临的数据偏移挑战,本文引入图论框架联合解决OOD泛化与检测问题,通过图邻接矩阵分解推导出可证明误差,实验验证了其优于现有方法的性能。

摘要:

在现代机器学习中,部署于真实场景的模型常遇到协变量和语义等数据偏移,导致OOD泛化和检测面临挑战。尽管这些问题已被分别广泛关注,但仍缺乏用于理论理解和实际应用的统一框架。为弥补这一空白,我们引入图论框架共同解决OOD泛化和检测问题。通过利用图表示,数据表示通过图邻接矩阵的分解获得,使我们能推导出量化OOD泛化和检测性能的可证明误差。实证结果表明,与现有方法相比具有竞争力的性能,从而验证了理论基础。代码公开于 https://github.com/deeplearning-wisc/graph-spectral-ood。

英文摘要:

In the context of modern machine learning, models deployed in real-world scenarios often encounter diverse data shifts like covariate and semantic shifts, leading to challenges in both out-of-distribution (OOD) generalization and detection. Despite considerable attention to these issues separately, a unified framework for theoretical understanding and practical usage is lacking. To bridge the gap, we introduce a graph-theoretic framework to jointly tackle both OOD generalization and detection problems. By leveraging the graph formulation, data representations are obtained through the factorization of the graph's adjacency matrix, enabling us to derive provable error quantifying OOD generalization and detection performance. Empirical results showcase competitive performance in comparison to existing methods, thereby validating our theoretical underpinnings. Code is publicly available at https://github.com/deeplearning-wisc/graph-spectral-ood.

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。

↑