[论文解读] Graph Condensation: A Survey

Xinyi Gao, Junliang Yu+4 more|arXiv (Cornell University)|Jan 22, 2024

Advanced Graph Neural Networks被引用 6

一句话总结

本综述通过四个标准系统化图凝缩（GC）方法——有效性、泛化性、公平性和效率性——并讨论优化策略与凝缩图生成、应用、挑战及未来方向。

ABSTRACT

The rapid growth of graph data poses significant challenges in storage, transmission, and particularly the training of graph neural networks (GNNs). To address these challenges, graph condensation (GC) has emerged as an innovative solution. GC focuses on synthesizing a compact yet highly representative graph, enabling GNNs trained on it to achieve performance comparable to those trained on the original large graph. The notable efficacy of GC and its broad prospects have garnered significant attention and spurred extensive research. This survey paper provides an up-to-date and systematic overview of GC, organizing existing research into five categories aligned with critical GC evaluation criteria: effectiveness, generalization, efficiency, fairness, and robustness. To facilitate an in-depth and comprehensive understanding of GC, this paper examines various methods under each category and thoroughly discusses two essential components within GC: optimization strategies and condensed graph generation. We also empirically compare and analyze representative GC methods with diverse optimization strategies based on the five proposed GC evaluation criteria. Finally, we explore the applications of GC in various fields, outline the related open-source libraries, and highlight the present challenges and novel insights, with the aim of promoting advancements in future research. The related resources can be found at https://github.com/XYGaoG/Graph-Condensation-Papers.

研究动机与目标

• 基于关键评价标准（有效性、泛化、公平性、效率）提供对GC方法的系统分类。
• 总结GC的最新进展，包括优化策略和凝缩图生成。
• 讨论GC在各领域的应用，并识别当前挑战与未来研究方向。
• 突出GC如何实现大规模图上GNN的高效训练，并支持终身学习和多任务场景。

提出的方法

• 对GC进行形式化定义，并引入中继模型f_theta以连接原始图与凝缩图。
• 将GC方法分类为四类，与评估标准对齐：有效GC、泛化GC、公平GC、高效GC。
• 回顾优化策略（梯度匹配、轨迹匹配、核岭回归、分布匹配）及它们对凝缩的影响。 0
• 分析凝缩图生成技术及其对下游任务和模型结构的影响。

实验结果

研究问题

• RQ1 如何有效地对GC方法进行分类，以反映其目标和评价标准？
• RQ2 哪些优化策略和凝缩图生成方法能最好地在不同体系结构和任务中保持任务性能？
• RQ3 GC方法在实践中如何解决泛化性、公平性与效率？
• RQ4 在真实世界应用中，GC面临的关键挑战与开放方向是什么？

主要发现

• GC方法被分成四类——有效、泛化、公平、高效——以实现不同目标。
• 优化策略包括梯度/轨迹匹配、核岭回归和分布匹配，以应对GC中的双层学习问题。
• 面向泛化的GC使用中继模型设计及谱方法/正则化技术，在不同模型和任务之间保持与任务相关的信息。
• 公平GC引入正则化或对抗模块，以降低凝缩图中的偏差放大。
• 高效GC通过如SGC式编码和一步匹配等方式加速编码、优化和图生成，在降低运行时间的同时保持性能。