![[2602.05358] Bayesian Neighborhood Adaptation for Graph Neural Networks](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.05358] Bayesian Neighborhood Adaptation for Graph Neural Networks
Summary
This paper presents a Bayesian framework for adapting neighborhood scopes in Graph Neural Networks (GNNs), enhancing their performance in node classification tasks by optimizing message-passing behavior.
Why It Matters
The research addresses a critical aspect of GNNs—determining the optimal neighborhood scope for aggregating information. By providing a Bayesian approach, it offers a more efficient and effective method for improving GNN performance, which is vital for applications in various domains such as social networks, biology, and recommendation systems.
Key Takeaways
- Introduces a Bayesian framework for neighborhood adaptation in GNNs.
- Improves expressivity and performance of GNNs in node classification tasks.
- Offers a solution to the inefficiencies of traditional two-stage approaches.
Computer Science > Machine Learning arXiv:2602.05358 (cs) [Submitted on 5 Feb 2026 (v1), last revised 12 Feb 2026 (this version, v2)] Title:Bayesian Neighborhood Adaptation for Graph Neural Networks Authors:Paribesh Regmi, Rui Li, Kishan KC View a PDF of the paper titled Bayesian Neighborhood Adaptation for Graph Neural Networks, by Paribesh Regmi and 2 other authors View PDF HTML (experimental) Abstract:The neighborhood scope (i.e., number of hops) where graph neural networks (GNNs) aggregate information to characterize a node's statistical property is critical to GNNs' performance. Two-stage approaches, training and validating GNNs for every pre-specified neighborhood scope to search for the best setting, is a time-consuming task and tends to be biased due to the search space design. How to adaptively determine proper neighborhood scopes for the aggregation process for both homophilic and heterophilic graphs remains largely unexplored. We thus propose to model the GNNs' message-passing behavior on a graph as a stochastic process by treating the number of hops as a beta process. This Bayesian framework allows us to infer the most plausible neighborhood scope for message aggregation simultaneously with the optimization of GNN parameters. Our theoretical analysis shows that the scope inference improves the expressivity of a GNN. Experiments on benchmark homophilic and heterophilic datasets show that the proposed method is compatible with state-of-the-art GNN variants, achie...
