Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models

Graphs arise across a wide spectrum of real-world applications, spanning biology, e-commerce, social networks, and more. This ubiquity naturally raises a fundamental question: Can we build a graph foundation model that leverages knowledge from multiple domains and generalizes effectively to entirely new ones? Achieving this goal, however, is challenging due to the substantial variation in graph characteristics across domains. While early efforts have explored cross-domain graph pre-training, many rely on auxiliary textual data to bridge semantic gaps between graphs, limiting their applicability to text-attributed graphs. In addition, integrating multiple source domains can introduce domain conflicts and uneven relevance to the target task, ultimately hindering robust generalization. To overcome these challenges, we propose MDGPT , a text-free graph learning framework that unifies and transfers knowledge across different graph domains. We begin by introducing a set of domain tokens that align diverse features from various domains, enabling coherent representation learning during pre-training. Then, we develop a two-stage prompting mechanism: the unifying prompt encodes domain-invariant semantics shared across multiple sources, while the mixing prompt selectively composes domain-specific signals to adapt the model to the target domain. We evaluate our approach on six benchmark datasets, where MDGPT achieves up to a 10.2% improvement over state-of-the-art methods, demonstrating its effectiveness in cross-domain generalization. (Codes are available at https://github.com/Nashchou/MDGPT .)

Authors

Institutions

Publication Details

Journal
ACM Transactions on Knowledge Discovery from Data
Published
2026-11-21
DOI
https://doi.org/10.1145/3862859
Citations
50
Primary Topic
Advanced Graph Neural Networks
Type
article
Field-Weighted Citation Impact
29.78
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models

Xingtong Yu, Yuan Fang, Chang Zhou, Xinming Zhang
50 citations
ACM Transactions on Knowledge Discovery from Data
Advanced Graph Neural Networks
29.78
article

Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models

Xingtong Yu, Yuan Fang, Chang Zhou, Xinming Zhang
article en
50 citations

Abstract

Graphs arise across a wide spectrum of real-world applications, spanning biology, e-commerce, social networks, and more. This ubiquity naturally raises a fundamental question: Can we build a graph foundation model that leverages knowledge from multiple domains and generalizes effectively to entirely new ones? Achieving this goal, however, is challenging due to the substantial variation in graph characteristics across domains. While early efforts have explored cross-domain graph pre-training, many rely on auxiliary textual data to bridge semantic gaps between graphs, limiting their applicability to text-attributed graphs. In addition, integrating multiple source domains can introduce domain conflicts and uneven relevance to the target task, ultimately hindering robust generalization. To overcome these challenges, we propose MDGPT , a text-free graph learning framework that unifies and transfers knowledge across different graph domains. We begin by introducing a set of domain tokens that align diverse features from various domains, enabling coherent representation learning during pre-training. Then, we develop a two-stage prompting mechanism: the unifying prompt encodes domain-invariant semantics shared across multiple sources, while the mixing prompt selectively composes domain-specific signals to adapt the model to the target domain. We evaluate our approach on six benchmark datasets, where MDGPT achieves up to a 10.2% improvement over state-of-the-art methods, demonstrating its effectiveness in cross-domain generalization. (Codes are available at https://github.com/Nashchou/MDGPT .)

ACM Transactions on Knowledge Discovery from Data
University of Science and Technology of China (CN), Chinese University of Hong Kong (HK), Singapore Management University (SG)
Openalex Percentile: Top 0%
Advanced Graph Neural Networks
29.78
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models — Xingtong Yu, Yuan Fang, et al. · ACM Transactions on Knowledge Discovery from Data (2026) | TGRS Research Map | TGRS