BeGin：面向图持续学习的丰富基准场景与易用框架
BeGin: Extensive Benchmark Scenarios and An Easy-to-use Framework for Graph Continual Learning
AI总结：
针对图持续学习缺乏标准设置、基准场景及实现复杂的问题，本文定义四类标准增量设置，提供35个基准场景，开发模块化易用框架BeGin，覆盖的增量设置与问题层级组合是最新基准的3倍，资源已公开。
摘要：
持续学习（Continual Learning, CL）是持续学习一系列任务的过程。现有大多数CL方法处理独立数据（如图像和文本），这类数据已有许多标准实验设置下的基准框架和结果。然而相比之下，针对图数据的CL方法（图CL）的研究相对不足，原因包括：(a) 缺乏标准实验设置，尤其是如何处理实例间的依赖关系；(b) 缺乏基准数据集和场景；(c) 依赖关系导致实现和评估的复杂度较高。本文中，针对(a)，我们为节点级、链路级和图级问题定义了四种标准增量设置（任务增量、类别增量、域增量和时间增量），拓展了此前的研究范围。针对(b)，我们基于24个真实世界图提供了35个基准场景。针对(c)，我们开发了BeGin，一个简单可靠的图CL框架。BeGin采用模块化设计，包含可复用的数据处理、算法设计和评估模块，因此易于扩展。特别是，评估模块与用户代码完全分离，以消除潜在错误。在基准结果方面，我们覆盖的增量设置与问题层级的组合数量是最新基准的3倍。该基准框架的所有资源已在https://github.com/ShinhwanKang/BeGin 公开。
英文摘要：
Continual Learning (CL) is the process of learning ceaselessly a sequence of tasks. Most existing CL methods deal with independent data (e.g., images and text) for which many benchmark frameworks and results under standard experimental settings are available. Compared to them, however, CL methods for graph data (graph CL) are relatively underexplored because of (a) the lack of standard experimental settings, especially regarding how to deal with the dependency between instances, (b) the lack of benchmark datasets and scenarios, and (c) high complexity in implementation and evaluation due to the dependency. In this paper, regarding (a) we define four standard incremental settings (task-, class-, domain-, and time-incremental) for node-, link-, and graph-level problems, extending the previously explored scope. Regarding (b), we provide 35 benchmark scenarios based on 24 real-world graphs. Regarding (c), we develop BeGin, an easy and fool-proof framework for graph CL. BeGin is easily extended since it is modularized with reusable modules for data processing, algorithm design, and evaluation. Especially, the evaluation module is completely separated from user code to eliminate potential mistakes. Regarding benchmark results, we cover 3x more combinations of incremental settings and levels of problems than the latest benchmark. All assets for the benchmark framework are publicly available at https://github.com/ShinhwanKang/BeGin.
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。
