Robust Graph Structure Learning under Heterophily
This addresses the challenge of handling heterophily in graph-based learning, which is crucial for applications with noisy real-world data, though it appears incremental as it builds on existing graph representation methods.
The paper tackles the problem of learning robust graph structures from noisy, heterophilic data, where connected nodes often belong to different classes, and demonstrates effectiveness through clustering and semi-supervised classification experiments.
Graph is a fundamental mathematical structure in characterizing relations between different objects and has been widely used on various learning tasks. Most methods implicitly assume a given graph to be accurate and complete. However, real data is inevitably noisy and sparse, which will lead to inferior results. Despite the remarkable success of recent graph representation learning methods, they inherently presume that the graph is homophilic, and largely overlook heterophily, where most connected nodes are from different classes. In this regard, we propose a novel robust graph structure learning method to achieve a high-quality graph from heterophilic data for downstream tasks. We first apply a high-pass filter to make each node more distinctive from its neighbors by encoding structure information into the node features. Then, we learn a robust graph with an adaptive norm characterizing different levels of noise. Afterwards, we propose a novel regularizer to further refine the graph structure. Clustering and semi-supervised classification experiments on heterophilic graphs verify the effectiveness of our method.