Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Zhengyu, Zhu, Yinlin, Li, Xunkai, Qiu, Ziang, Li, Rong-Hua, Wang, Guoren, Zhou, Chenghu
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2510.07755
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916998086131712
author Wu, Zhengyu
Zhu, Yinlin
Li, Xunkai
Qiu, Ziang
Li, Rong-Hua
Wang, Guoren
Zhou, Chenghu
author_facet Wu, Zhengyu
Zhu, Yinlin
Li, Xunkai
Qiu, Ziang
Li, Rong-Hua
Wang, Guoren
Zhou, Chenghu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07755
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
Wu, Zhengyu
Zhu, Yinlin
Li, Xunkai
Qiu, Ziang
Li, Rong-Hua
Wang, Guoren
Zhou, Chenghu
Machine Learning
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.
title FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
topic Machine Learning
url https://arxiv.org/abs/2510.07755