通过对抗性边掩码学习跨域不变图结构，提升模型泛化能力。
EdgeMask-DG*: Learning Domain-Invariant Graph Structures via Adversarial Edge Masking
- 设计对抗性边掩码机制，动态识别关键不变边
- 在Cora OOD上最差域准确率达78.0%，提升3.8个百分点
- 适合处理拓扑噪声大或领域差异显著的图数据
结构漂移对图神经网络构成重大挑战，因图拓扑作为协变量可在不同领域间变化。现有领域泛化方法依赖固定结构增强或全局扰动图训练，无法定位哪些边编码了域不变信息。我们认为，域不变结构信息并非依附于单一拓扑，而是存在于基于拓扑与特征相似性生成的多图结构共识中。为此，我们提出EdgeMask-DG，一种新颖的极小极大算法，其中边掩码器在稀疏性约束下学习最坏情况的连续掩码，迫使任务图神经网络在对抗性结构扰动下仍保持性能。在此基础上，我们进一步提出EdgeMask-DG*，将该对抗掩码原则应用于融合原始拓扑与特征衍生边的增强图，使模型即使在原始拓扑噪声大或具领域特异性时也能发现不变性。EdgeMask-DG*是首个系统结合自适应对抗拓扑搜索与特征增强图的方法。我们从鲁棒优化角度为该方法提供形式化论证。实验表明，EdgeMask-DG*在多样图领域泛化基准（包括引文网络、社交网络与时间图）上达到新最优性能。尤其在Cora OOD基准上，最差域准确率提升至78.0%，较先前最优结果（74.2%）提高3.8个百分点。
原文摘要 · Abstract (English)
Structural shifts pose a significant challenge for graph neural networks, as graph topology acts as a covariate that can vary across domains. Existing domain generalization methods rely on fixed structural augmentations or training on globally perturbed graphs, mechanisms that do not pinpoint which specific edges encode domain-invariant information. We argue that domain-invariant structural information is not rigidly tied to a single topology but resides in the consensus across multiple graph structures derived from topology and feature similarity. To capture this, we first propose EdgeMask-DG, a novel min-max algorithm where an edge masker learns to find worst-case continuous masks subject to a sparsity constraint, compelling a task GNN to perform effectively under these adversarial structural perturbations. Building upon this, we introduce EdgeMask-DG*, an extension that applies this adversarial masking principle to an enriched graph. This enriched graph combines the original topology with feature-derived edges, allowing the model to discover invariances even when the original topology is noisy or domain-specific. EdgeMask-DG* is the first to systematically combine adaptive adversarial topology search with feature-enriched graphs. We provide a formal justification for our approach from a robust optimization perspective. We demonstrate that EdgeMask-DG* achieves new state-of-the-art performance on diverse graph domain generalization benchmarks, including citation networks, social networks, and temporal graphs. Notably, on the Cora OOD benchmark, EdgeMask-DG* lifts the worst-case domain accuracy to 78.0\%, a +3.8 pp improvement over the prior state of the art (74.2\%). The source code for our experiments can be found here: https://anonymous.4open.science/r/TMLR-EAEF/
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。