面向动态图的时序记忆感知在线测试时自适应方法
Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs
查看机构详情
- Griffith University（格里菲斯大学）
- RMIT University（皇家墨尔本理工大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文针对动态图测试时自适应的研究空白，提出DGOTTA框架，通过三个模块提升DGNN在分布偏移下的泛化性能，经多数据集实验验证有效。
中文摘要 AI 辅助
图上的测试时自适应（Test-time adaptation, TTA）旨在将在训练图上训练好的图神经网络（Graph Neural Network, GNN）适配到测试图，以应对可能损害模型泛化能力和测试时推理性能的分布偏移。尽管现有研究已探索了静态图上的TTA，但针对动态图的研究仍存在空白，动态图由动态图神经网络（Dynamic GNN, DGNN）建模，其结构连接和节点语义会随时间持续演化，这使得适配DGNN以获得可靠的测试时性能极具挑战性。为填补该空白，本文提出一种名为DGOTTA的新型框架，用于在测试时有效适配已训练好的DGNN。DGOTTA包含三个模块：（1）时序感知增强模块，用于扩展测试动态图的多样性，以应对复杂的时序和空间偏移；（2）记忆感知模型预测模块，用于缓解灾难性遗忘；（3）一致性引导在线适配模块，用于强制时序对齐和记忆平滑性。在三个真实世界数据集和四个DGNN骨干网络上开展的大量实验表明，DGOTTA在多种分布偏移和多种模型架构下均能显著提升泛化性能。
英文摘要
Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which involves potential distribution shifts that may harm model generalization and test-time inference. While recent efforts have investigated TTA on static graphs, there is still a research gap on dynamic graphs learned with dynamic GNN (DGNN) models, where both structural connectivity and node semantics evolve continuously over time. This makes adapting a DGNN model for reliable test-time performance substantially challenging. To fill this gap, in this work, we propose a novel framework of temporal memory-aware Online Test-Time Adaptation on Dynamic Graphs, named DGOTTA, to effectively adapt well-trained DGNNs during test time. Specifically, the proposed DGOTTA contains three modules: (1) temporal-aware augmentation, to extend the diversity of test dynamic graphs for addressing complex temporal and spatial shifts; (2) memory-aware model prediction, to alleviate catastrophic forgetting; (3) consistency-guided online adaptation, to enforce temporal alignment and memory smoothness. Extensive experiments on three real-world datasets and four DGNN backbones demonstrate that DGOTTA significantly improves generalization under diverse distribution shifts and multiple model architectures.
