FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
Preprint
Abstract
Foundation models have shown remarkable cross-domain generalization in language and vision, inspiring the development of graph foundation models (GFMs). However, existing GFMs typically assume centralized access to multi-domain graphs, which is often infeasible due to privacy and institutional constraints. Federated Graph Foundation Models (FedGFMs) address this limitation, but their effectiveness fundamentally hinges on constructing a robust global codebook that achieves intra-domain coherence by consolidating mutually reinforcing semantics within each domain, while also maintaining inter-domain diversity by retaining heterogeneous knowledge across domains. To this end, we propose FedBook, a unified federated graph foundation codebook that systematically aggregates clients' local codebooks during server-side federated pre-training. FedBook follows a two-phase process: (1) Intra-domain Collaboration, where low-frequency tokens are refined by referencing more semantically reliable high-frequency tokens across clients to enhance domain-specific coherence; and (2) Inter-domain Integration, where client contributions are weighted by the semantic distinctiveness of their codebooks during the aggregation of the global GFM, thereby preserving cross-domain diversity. Extensive experiments on 8 benchmarks across multiple domains and tasks demonstrate that FedBook consistently outperforms 21 baselines, including isolated supervised learning, FL/FGL, federated adaptations of centralized GFMs, and FedGFM techniques.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Benchmarking Graph Foundation Models2025
- UniGraph: Learning a Unified Cross-Domain Foundation Model for Text-Attributed Graphs2025
- GraphGPT: Graph Instruction Tuning for Large Language Models2024
- AdaFGL: A New Paradigm for Federated Node Classification with Topology Heterogeneity2024
- FedGL: Federated graph learning framework with global self-supervisionInformation Sciences, 2023
- FedEgo: Privacy-preserving Personalized Federated Graph Learning with Ego-graphsACM Transactions on Knowledge Discovery From Data, 2023
- Privacy-Preserving Graph Machine Learning from Data to Computation: A SurveyACM SIGKDD Explorations Newsletter, 2023
- GCC2020
- MoleculeNet: a benchmark for molecular machine learningChemical Science, 2017
- A Fast and High Quality Multilevel Scheme for Partitioning Irregular GraphsSIAM Journal on Scientific Computing, 1998