5 papers
Out-of-Distribution Graph Models Merging
Yidi Wang, Ziyue Qiao, Jiawei Gu +4
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 doma…
Gradient Short-Circuit: Efficient Out-of-Distribution Detection via Feature Intervention
Jiawei Gu, Ziyue Qiao, Zechao Li
Out-of-Distribution (OOD) detection is critical for safely deploying deep models in open-world environments, where inputs may lie outside the training distribution. During inferenc…
NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration
Jiawei Gu, Ziyue Qiao, Xiao Luo
Graph Neural Networks (GNNs) have shown remarkable performance across various domains, yet they often struggle with model bias, particularly in the presence of class imbalance. Thi…
SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps
Jiawei Gu, Ziyue Qiao, Zechao Li
The task of graph-level out-of-distribution (OOD) detection is crucial for deploying graph neural networks in real-world settings. In this paper, we observe a significant differenc…
GCAL: Adapting Graph Models to Evolving Domain Shifts
Ziyue Qiao, Qianyi Cai, Hao Dong +5
This paper addresses the challenge of graph domain adaptation on evolving, multiple out-of-distribution (OOD) graphs. Conventional graph domain adaptation methods are confined to s…