Towards Data-centric Graph Machine Learning: Review and Outlook
Xin Zheng , Yixin Liu Monash UniversityMelbourneVICAustralia3800 , Zhifeng Bao RMIT UniversityMelbourneVICAustralia , Meng Fang University of LiverpoolLiverpoolUK , Xia Hu Rice UniversityHoustonUS , Alan Wee-Chung Liew and Shirui Pan Griffith UniversityGold CoastQueenslandAustralia
Abstract
Data-centric AI, with its primary focus on the collection, management, and utilization of data to drive AI models and applications, has attracted increasing attention in recent years. In this article, we conduct an in-depth and comprehensive review, offering a forward-looking outlook on the current efforts in data-centric AI pertaining to graph data—the fundamental data structure for representing and capturing intricate dependencies among massive and diverse real-life entities. We introduce a systematic framework, Data-centric Graph Machine Learning (DC-GML), that encompasses all stages of the graph data lifecycle, including graph data collection, exploration, improvement, exploitation, and maintenance. A thorough taxonomy of each stage is presented to answer three critical graph-centric questions: (1) how to enhance graph data availability and quality; (2) how to learn from graph data with limited-availability and low-quality; (3) how to build graph MLOps systems from the graph data-centric view. Lastly, we pinpoint the future prospects of the DC-GML domain, providing insights to navigate its advancements and applications 111Github Page: https://github.com/Data-Centric-GraphML/awe
中文速览
真实世界中的图数据（Graph Data）普遍存在质量差、规模小、噪声多等问题，严重制约了图神经网络（Graph Neural Network, GNN）的实际表现，而现有研究大多聚焦于模型本身的改进，忽视了数据侧的系统性治理。为此，本文提出了一个名为"以数据为中心的图机器学习"（Data-centric Graph Machine Learning, DC-GML）的系统性框架，将图数据的完整生命周期划分为采集、探索、改善、利用和维护五个阶段，并分别梳理了各阶段的方法体系，重点回答三个核心问题：如何提升图数据的可用性与质量、如何在数据有限或低质的条件下有效学习、以及如何从数据视角构建图机器学习的运营（MLOps）流程。综合来看，该框架覆盖了图数据去噪、增强、标注、自监督学习、数据估值等大量前沿进展，是目前首个专门面向图结构数据的数据中心式AI综述，为推动图学习从"模型驱动"向"数据驱动"转型提供了系统性路线图。
原文 arXiv:2309.10979;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2309.10979v1