Out-of-Distribution Graph Models Merging

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.

@article{wang2025_2506.03674,
  title={ Out-of-Distribution Graph Models Merging },
  author={ Yidi Wang and Jiawei Gu and pei Xiaobing and Xubin Zheng and Xiao Luo and Pengyang Wang and Ziyue Qiao },
  journal={arXiv preprint arXiv:2506.03674},
  year={ 2025 }
}