AGALE：一种图感知的持续学习评估框架
AGALE: A Graph-Aware Continual Learning Evaluation Framework
AI总结：
本文提出图感知持续学习评估框架AGALE，支持单标签与多标签节点分类，通过新增量设置和数据划分算法，系统比较持续学习、持续图学习与动态图学习方法，并揭示同质性对性能的影响。
摘要：
近年来，持续学习（CL）技术在从流式数据中学习并在顺序任务间保持知识方面取得了显著进展，尤其是在欧几里得数据领域。为了促进公平评估并识别持续学习环境中的挑战，已有若干评估框架被提出，主要关注欧几里得数据上的单标签和多标签分类任务。然而，当输入数据为图结构时，这些评估框架并不能直接适用，因为它们没有考虑图中固有的拓扑结构。现有的持续图学习（CGL）评估框架主要集中于节点分类（NC）任务中的单标签场景。这一关注点忽视了多标签场景的复杂性，在多标签场景中，节点可能同时隶属于多个标签，并同时参与多个任务。我们开发了一个图感知评估框架（AGALE），该框架同时适应单标签和多标签节点，解决了以往评估框架的局限性。特别地，我们定义了新的增量设置，并设计了针对持续图学习数据集的数据划分算法。我们进行了大量实验，比较了来自持续学习、持续图学习和动态图学习（DGL）领域的方法。我们从理论上分析了AGALE，并就同质性在比较方法性能中的作用提供了新的见解。我们在 https://github.com/Tianqi-py/AGALE 发布了我们的框架。
英文摘要：
In recent years, continual learning (CL) techniques have made significant progress in learning from streaming data while preserving knowledge across sequential tasks, particularly in the realm of euclidean data. To foster fair evaluation and recognize challenges in CL settings, several evaluation frameworks have been proposed, focusing mainly on the single- and multi-label classification task on euclidean data. However, these evaluation frameworks are not trivially applicable when the input data is graph-structured, as they do not consider the topological structure inherent in graphs. Existing continual graph learning (CGL) evaluation frameworks have predominantly focussed on single-label scenarios in the node classification (NC) task. This focus has overlooked the complexities of multi-label scenarios, where nodes may exhibit affiliations with multiple labels, simultaneously participating in multiple tasks. We develop a graph-aware evaluation (\agale) framework that accommodates both single-labeled and multi-labeled nodes, addressing the limitations of previous evaluation frameworks. In particular, we define new incremental settings and devise data partitioning algorithms tailored to CGL datasets. We perform extensive experiments comparing methods from the domains of continual learning, continual graph learning, and dynamic graph learning (DGL). We theoretically analyze \agale and provide new insights about the role of homophily in the performance of compared methods. We release our framework at https://github.com/Tianqi-py/AGALE.
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。
