Explaining and Adapting Graph Conditional Shift
This addresses performance degradation in GNNs under distribution shift, which is a domain-specific problem, but the approach is incremental as it builds on existing adaptation techniques.
The paper tackled the vulnerability of Graph Neural Networks (GNNs) to distribution shift by analyzing conditional shift and proposing an adaptation method, resulting in up to 10% ROC AUC improvement in synthetic experiments and robust performance in node and graph classification tasks.
Graph Neural Networks (GNNs) have shown remarkable performance on graph-structured data. However, recent empirical studies suggest that GNNs are very susceptible to distribution shift. There is still significant ambiguity about why graph-based models seem more vulnerable to these shifts. In this work we provide a thorough theoretical analysis on it by quantifying the magnitude of conditional shift between the input features and the output label. Our findings show that both graph heterophily and model architecture exacerbate conditional shifts, leading to performance degradation. To address this, we propose an approach that involves estimating and minimizing the conditional shift for unsupervised domain adaptation on graphs. In our controlled synthetic experiments, our algorithm demonstrates robustness towards distribution shift, resulting in up to 10% absolute ROC AUC improvement versus the second-best algorithm. Furthermore, comprehensive experiments on both node classification and graph classification show its robust performance under various distribution shifts.