A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Ziwen, Su, Yixin, Li, Yuhua, Zou, Yixiong, Li, Ruixuan, Zhang, Rui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915286780739584
author Zhao, Ziwen
Su, Yixin
Li, Yuhua
Zou, Yixiong
Li, Ruixuan
Zhang, Rui
author_facet Zhao, Ziwen
Su, Yixin
Li, Yuhua
Zou, Yixiong
Li, Ruixuan
Zhang, Rui
contents Graph self-supervised learning (SSL) is now a go-to method for pre-training graph foundation models (GFMs). There is a wide variety of knowledge patterns embedded in the graph data, such as node properties and clusters, which are crucial to learning generalized representations for GFMs. However, existing surveys of GFMs have several shortcomings: they lack comprehensiveness regarding the most recent progress, have unclear categorization of self-supervised methods, and take a limited architecture-based perspective that is restricted to only certain types of graph models. As the ultimate goal of GFMs is to learn generalized graph knowledge, we provide a comprehensive survey of self-supervised GFMs from a novel knowledge-based perspective. We propose a knowledge-based taxonomy, which categorizes self-supervised graph models by the specific graph knowledge utilized. Our taxonomy consists of microscopic (nodes, links, etc.), mesoscopic (context, clusters, etc.), and macroscopic knowledge (global structure, manifolds, etc.). It covers a total of 9 knowledge categories and more than 25 pretext tasks for pre-training GFMs, as well as various downstream task generalization strategies. Such a knowledge-based taxonomy allows us to re-examine graph models based on new architectures more clearly, such as graph language models, as well as provide more in-depth insights for constructing GFMs.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16137
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
Zhao, Ziwen
Su, Yixin
Li, Yuhua
Zou, Yixiong
Li, Ruixuan
Zhang, Rui
Machine Learning
Social and Information Networks
Graph self-supervised learning (SSL) is now a go-to method for pre-training graph foundation models (GFMs). There is a wide variety of knowledge patterns embedded in the graph data, such as node properties and clusters, which are crucial to learning generalized representations for GFMs. However, existing surveys of GFMs have several shortcomings: they lack comprehensiveness regarding the most recent progress, have unclear categorization of self-supervised methods, and take a limited architecture-based perspective that is restricted to only certain types of graph models. As the ultimate goal of GFMs is to learn generalized graph knowledge, we provide a comprehensive survey of self-supervised GFMs from a novel knowledge-based perspective. We propose a knowledge-based taxonomy, which categorizes self-supervised graph models by the specific graph knowledge utilized. Our taxonomy consists of microscopic (nodes, links, etc.), mesoscopic (context, clusters, etc.), and macroscopic knowledge (global structure, manifolds, etc.). It covers a total of 9 knowledge categories and more than 25 pretext tasks for pre-training GFMs, as well as various downstream task generalization strategies. Such a knowledge-based taxonomy allows us to re-examine graph models based on new architectures more clearly, such as graph language models, as well as provide more in-depth insights for constructing GFMs.
title A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspective
topic Machine Learning
Social and Information Networks
url https://arxiv.org/abs/2403.16137