Author Identifier (ORCID)
Abstract
Community search is a fundamental graph-based retrieval problem that aims to identify a query-dependent subgraph whose nodes exhibit strong internal connectivity. While recent learning-based methods improve retrieval effectiveness via graph representation learning, they follow a ''one-use-one-train'' paradigm that requires retraining or fine-tuning for each target graph, leading to high data dependency, high training costs, and limited generalization. To handle this, we propose OFA-CS, a ''one-for-all'' community search framework trained once on source datasets and directly deployed to arbitrary unseen graphs without retraining or fine-tuning, while preserving strong performance. Specifically, we introduce a Spectral-Aware Feature Alignment module to unify feature dimensionality and align cross-domain semantics in a community-aware manner. We further develop a Graph Diffusion Tokenized Transformer that constructs hybrid token sequences from local and global structural contexts for Transformer encoding, and applies diffusion-based refinement to mitigate distribution shifts on unseen graphs. With the unified representations, communities are efficiently retrieved via a modularity-driven search procedure. Extensive experiments on diverse real-world graphs demonstrate that OFA-CS achieves strong cross-domain generalization and competitive retrieval effectiveness against state-of-the-art methods, without requiring target-domain supervision.
Keywords
community search, diffusion model, graph transformer
Document Type
Conference Proceeding
Date of Publication
7-19-2026
Publication Title
SIGIR '26: Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval
Publisher
Association for Computing Machinery
School
School of Business and Law
Funding Information
This work was supported in part by the National Natural Science Foundation of China (Nos. 52574191 and 62072220); Young top talents of Liaoning "Xingliao Talent Program" (No.XLYC2203003); Liaoning Provincial Department of Education Research Platform Construction Project (No.LJ232510140001); National Science and Technology Major Project (No.2024ZD1700104); Central Government Guides Local Science and Technology Development Fund (Liaoning Province Free Exploration Category-Provincial Youth A) (No.2026JH6/101100002); the Natural Science Foundation ofLiaoning Province (No.2025-MSLH-300); the Australian Research Council (ARC) via Discovery Early Career Researcher Award (No.DE230100366); and Google Foundational Science 2025 Award.
Funding received from the Australian Research Council (ARC)
DE230100366
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
ISBN
[9798400725999]
First Page
1060
Last Page
1071
Recommended Citation
Li, M., Zhao, Z., Ding, L., Borovica-Gajic, R., Yao, Z., & Li, J. (2026, July). One-for-all community search on unseen graphs. In Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 1060-1071). Association for Computing Machinery. https://doi.org/10.1145/3805712.3809594