GCAL：使图模型适应不断演化的领域偏移
GCAL: Adapting Graph Models to Evolving Domain Shifts
AI总结：
本文提出GCAL方法，通过双层优化（适应与生成记忆）解决图域适应中的持续偏移与灾难性遗忘问题，实验证明其在适应性和知识保留上优于现有方法。
摘要：
本文解决了在持续演化的多个分布外（OOD）图上的图域适应挑战。传统的图域适应方法局限于单步适应，使其在处理连续领域偏移时效果不佳，并容易发生灾难性遗忘。本文引入了图持续自适应学习（GCAL）方法，旨在增强模型在各种图域中的可持续性和适应性。GCAL采用双层优化策略。“适应”阶段使用信息最大化方法，通过新图域微调模型，同时重新适应过去的记忆以缓解遗忘。与此同时，由信息瓶颈理论推导出的理论下界指导的“生成记忆”阶段，涉及一个变分记忆图生成模块，将原始图压缩为记忆。广泛的实验评估表明，GCAL在适应性和知识保留方面显著优于现有方法。
英文摘要：
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.
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。
