发表机构
ShanghaiTech University; University of Illinois Urbana-Champaign; The Pennsylvania State University（上海科技大学; 伊利诺伊大学厄巴纳-香槟分校; 宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出Co-Train与Dual-Space Retrieval两个框架，利用自监督表示互补信息改进图神经网络分布外节点分类，在多个基准上优于强监督基线。
AI 中文摘要
分布外（OOD）泛化对图神经网络（GNNs）而言仍然具有挑战性，因为图分布可能随时间和领域发生显著变化。监督和图自监督表示学习受不同目标引导，提供不同的图表示视角。在本工作中，我们研究自监督表示（SSL）能否提供互补信号以改进监督式OOD节点分类。我们开发了两个与骨干网络无关的框架，在学习与预测的不同阶段利用此类信息。Co-Train联合学习监督与SSL表示，并在训练过程中自适应地整合它们；而Dual-Space Retrieval在两个表示空间中进行非参数预测，并在推理时通过置信度感知融合结合其预测。监督和SSL编码器分别参数化，不必共享相同的GNN架构。我们在四个涵盖时间与跨域分布偏移的图基准上评估了多个GNN骨干和两种不同的SSL目标（DGI和GRACE）。大量实验表明，Co-Train持续优于强监督OOD基线，而Dual-Space Retrieval作为灵活的非参数替代方案取得了具有竞争力的性能。不同骨干和SSL目标下的结果，连同表示分析和消融研究，证明SSL表示为监督表示提供互补信息，并能在多种设置下改进OOD节点分类。
英文摘要
Out-of-distribution (OOD) generalization remains challenging for graph neural networks (GNNs), as graph distributions can vary substantially across time and domains. Supervised and self-supervised graph representation learning are guided by distinct objectives and offer different perspectives on graph representations. In this work, we study whether self-supervised representations (SSL) can provide complementary signals to improve supervised OOD node classification. We develop two backbone-agnostic frameworks that exploit such information at different stages of learning and prediction. Co-Train jointly learns supervised and SSL representations and adaptively integrates them during training, while Dual-Space Retrieval performs non-parametric prediction in the two representation spaces and combines their predictions through confidence-aware fusion at inference time. The supervised and SSL encoders are separately parameterized and need not share the same GNN architecture. We evaluate multiple GNN backbones and two distinct SSL objectives, DGI and GRACE, on four graph benchmarks spanning temporal and cross-domain distribution shifts. Extensive experiments show that Co-Train consistently outperforms strong supervised OOD baselines, while Dual-Space Retrieval achieves competitive performance as a flexible non-parametric alternative. Results across different backbones and SSL objectives, together with representation analyses and ablations, demonstrate that SSL representations provide complementary information to supervised representations and can improve OOD node classification across diverse settings.
