用图论方法统一解决模型在分布外数据上的泛化与检测问题。
Bridging OOD Detection and Generalization: A Graph-Theoretic View
- 基于图邻接矩阵分解获取数据表示
- 理论证明可量化分布外泛化与检测误差
- 适合关注模型鲁棒性与理论分析的研究者
现代机器学习模型在真实场景中常遭遇协变量和语义数据偏移，导致分布外（OOD）泛化与检测面临挑战。尽管这两个问题各自受到广泛关注，但缺乏统一的理论框架与实用方法。为此，本文提出一种图论框架，联合解决 OOD 泛化与检测问题。通过图结构建模，利用邻接矩阵分解获得数据表示，进而推导出可证明的误差界，用于量化 OOD 泛化与检测性能。实验表明，该方法在多个基准上表现优于现有方法，验证了其理论有效性。代码已公开于 https://github.com/deeplearning-wisc/graph-spectral-ood。
原文摘要 · Abstract (English)
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.
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。