基于必要性与充分性概率统一图分布外泛化的不变性与伪相关性
Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency
AI总结：
针对图分布外泛化中语义子图丢失或冗余的问题，提出统一框架PNSIS，利用必要性与充分性概率提取不变子图，并结合伪相关子图以集成方式增强鲁棒性，在多个基准上优于现有技术。
摘要：
图分布外（OOD）要求在有偏数据上训练的模型能够泛化到未见测试数据，在现实世界中有大量应用。最主流的方法之一是通过环境增强的帮助，对齐原始数据和增强数据来提取不变子图。然而，这些解决方案可能导致语义子图的丢失或冗余，进而导致次优泛化。为了应对这一挑战，我们提出了一个统一框架，利用必要性与充分性概率来提取不变子结构（PNSIS）。不仅如此，该框架还进一步利用伪相关子图以集成方式提升泛化性能，从而增强在噪声数据上的鲁棒性。具体而言，我们首先考虑图数据的数据生成过程。在温和条件下，我们表明可以通过最小化一个基于必要性与充分性概率理论进展构建的上界来提取不变子图。为了进一步连接理论与算法，我们设计了PNSIS模型，该模型包含一个用于不变图学习的不变子图提取器，以及用于增强泛化的不变子图和伪相关子图分类器。实验结果表明，我们的PNSIS模型在多个基准上的图OOD任务中优于最先进的技术，突显了其在现实场景中的有效性。
英文摘要：
Graph Out-of-Distribution (OOD), requiring that models trained on biased data generalize to the unseen test data, has a massive of real-world applications. One of the most mainstream methods is to extract the invariant subgraph by aligning the original and augmented data with the help of environment augmentation. However, these solutions might lead to the loss or redundancy of semantic subgraph and further result in suboptimal generalization. To address this challenge, we propose a unified framework to exploit the Probability of Necessity and Sufficiency to extract the Invariant Substructure (PNSIS). Beyond that, this framework further leverages the spurious subgraph to boost the generalization performance in an ensemble manner to enhance the robustness on the noise data. Specificially, we first consider the data generation process for graph data. Under mild conditions, we show that the invariant subgraph can be extracted by minimizing an upper bound, which is built on the theoretical advance of probability of necessity and sufficiency. To further bridge the theory and algorithm, we devise the PNSIS model, which involves an invariant subgraph extractor for invariant graph learning as well invariant and spurious subgraph classifiers for generalization enhancement. Experimental results demonstrate that our \textbf{PNSIS} model outperforms the state-of-the-art techniques on graph OOD on several benchmarks, highlighting the effectiveness in real-world scenarios.
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。
