Multi-Domain Graph Foundation Models: Robust Knowledge Transfer via Topology Alignment

2025/02/04 by Shuo Wang, Bokui Wang, Wang, Shuo +5 · 14 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Distributed and Parallel Computing Systems #Educational Technology and Assessment #FOS: Computer and information sciences #Machine Learning (cs.LG) #Social and Information Networks (cs.SI)

paper · pdf · doi:10.48550/arxiv.2502.02017

openalex publication_date 2025/02/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent advances in CV and NLP have inspired researchers to develop general-purpose graph foundation models through pre-training across diverse domains. However, a fundamental challenge arises from the substantial differences in graph topologies across domains. Additionally, real-world graphs are often sparse and prone to noisy connections and adversarial attacks. To address these issues, we propose the Multi-Domain Graph Foundation Model (MDGFM), a unified framework that aligns and leverages cross-domain topological information to facilitate robust knowledge transfer. MDGFM bridges different domains by adaptively balancing features and topology while refining original graphs to eliminate noise and align topological structures. To further enhance knowledge transfer, we introduce an efficient prompt-tuning approach. By aligning topologies, MDGFM not only improves multi-domain pre-training but also enables robust knowledge transfer to unseen domains. Theoretical analyses provide guarantees of MDGFM's effectiveness and domain generalization capabilities. Extensive experiments on both homophilic and heterophilic graph datasets validate the robustness and efficacy of our method.

Cited by

• UniCom: Towards a Unified and Cohesiveness-aware Framework for Community Search and Detection
• Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
• SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation
• Privacy Auditing of Multi-domain Graph Pre-trained Model under Membership Inference Attacks
• GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning
• Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
• Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning
• One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
• GraphPFN: A Prior-Data Fitted Graph Foundation Model
• What Makes Graph Unified? Principles and Generative Sliding-Window Transformer for Graph Foundation Models
• Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
• Turning Tabular Foundation Models into Graph Foundation Models
• GraphProp: Training the Graph Foundation Models using Graph Properties

Related

• Text-Free Multi-domain Graph Pre-training: Toward Graph Foundation Models
• SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation
• Towards Graph Foundation Models: A Transferability Perspective
• Towards Text-free Graph Foundation Models: Rethinking Multi-Domain Graph Contrastive Learning
• Augmenting Knowledge Transfer across Graphs