Out-of-Distribution Graph Models Merging

ICLR 2026 Conference Submission16544 Authors

Keywords: Graph Models Merging, Source-Free Domain Generalization, Graph Neural Networks

TL;DR: Graph Models Merging for Graph OOD

Abstract: This paper studies a novel problem of out-of-distribution graph models merging, which aims to construct a generalized model from multiple graph models pre-trained on different domains with distribution discrepancy. This problem is challenging because of the difficulty in learning domain-invariant knowledge implicitly in model parameters and consolidating expertise from potentially heterogeneous GNN backbones. In this work, we propose a graph generation strategy that instantiates the mixture distribution of multiple domains. Then, we merge and fine-tune the pre-trained graph models via a MoE module and a masking mechanism for generalized adaptation. Our framework is architecture-agnostic and can operate without any source/target domain data. Both theoretical analysis and experimental results demonstrate the effectiveness of our approach in addressing the model generalization problem.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Submission Number: 16544