提出GCAL方法，让图模型持续适应动态变化的图数据。
GCAL: Adapting Graph Models to Evolving Domain Shifts
- 采用双阶段优化：先适应新图，再生成记忆以防止遗忘。
- 在多个演化图数据集上显著提升适应能力与知识保留率。
- 适合需要长期学习图结构变化的场景，如社交网络分析。
本文针对演化中的多源域外（OOD）图数据上的图领域自适应挑战。传统方法仅支持单步适应，难以应对连续域偏移且易发生灾难性遗忘。本文提出图持续自适应学习（GCAL）方法，旨在提升模型在不同图域间的可持续性与适应性。GCAL采用双层优化策略：在“适应”阶段，通过信息最大化方法微调模型以适配新图域，同时重激活旧有记忆以缓解遗忘；在“生成记忆”阶段，基于信息瓶颈理论导出的理论下界，引入变分记忆图生成模块，将原始图压缩为紧凑记忆。大量实验表明，GCAL在适应能力和知识保留方面显著优于现有方法。
原文摘要 · Abstract (English)
This paper addresses the challenge of graph domain adaptation on evolving, multiple out-of-distribution (OOD) graphs. Conventional graph domain adaptation methods are confined to single-step adaptation, making them ineffective in handling continuous domain shifts and prone to catastrophic forgetting. This paper introduces the Graph Continual Adaptive Learning (GCAL) method, designed to enhance model sustainability and adaptability across various graph domains. GCAL employs a bilevel optimization strategy. The "adapt" phase uses an information maximization approach to fine-tune the model with new graph domains while re-adapting past memories to mitigate forgetting. Concurrently, the "generate memory" phase, guided by a theoretical lower bound derived from information bottleneck theory, involves a variational memory graph generation module to condense original graphs into memories. Extensive experimental evaluations demonstrate that GCAL substantially outperforms existing methods in terms of adaptability and knowledge retention.
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。