在线连续图学习
Online Continual Graph Learning
AI总结：
本文提出在线持续图学习（OCGL）框架，通过严格资源约束下的节点级持续学习，实现对动态图的高效在线预测。
摘要：
持续学习（CL）旨在在减轻灾难性遗忘的同时逐步获取新知识。在此设定中，在线持续学习（OCL）专注于从数据流中的单个或小批量观测中及时且逐步地更新模型。将OCL扩展到图结构数据至关重要，因为许多现实世界网络随时间演变，并需要及时的在线预测。然而，现有的持续或流式图学习方法通常假设可以访问完整的图快照或多次遍历任务，这违反了在线设置的效率约束。为了解决这一差距，我们引入了在线持续图学习（OCGL）设定，该设定在严格的内存和计算预算下正式化了在演变图上的节点级持续学习。OCGL定义了模型如何逐步处理节点级信息流，同时保持随时推理并尊重资源约束。我们进一步建立了一个包含七个数据集和九种CL策略的综合性基准，这些策略已适配到OCGL设定中，从而实现标准化的评估设置。最后，我们提出了一个简洁但具有竞争力的基线模型，受我们基准测试结果启发，该模型在高效率下实现了强大的经验表现。
英文摘要：
Continual Learning (CL) aims to incrementally acquire new knowledge while mitigating catastrophic forgetting. Within this setting, Online Continual Learning (OCL) focuses on updating models promptly and incrementally from single or small batches of observations from a data stream. Extending OCL to graph-structured data is crucial, as many real-world networks evolve over time and require timely, online predictions. However, existing continual or streaming graph learning methods typically assume access to entire graph snapshots or multiple passes over tasks, violating the efficiency constraints of the online setting. To address this gap, we introduce the Online Continual Graph Learning (OCGL) setting, which formalizes node-level continual learning on evolving graphs under strict memory and computational budgets. OCGL defines how a model incrementally processes a stream of node-level information while maintaining anytime inference and respecting resource constraints. We further establish a comprehensive benchmark comprising seven datasets and nine CL strategies, suitably adapted to the OCGL setting, enabling a standardized evaluation setup. Finally, we present a minimalistic yet competitive baseline for OCGL, inspired by our benchmarking results, that achieves strong empirical performance with high efficiency.
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。
