Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks
Graph Neural Networks (GNNs) exhibit excellent performance when graphs have strong homophily property, i.e. connected nodes have the same labels. However, they perform poorly on heterophilic graphs. Several approaches address the issue of heterophily by proposing models that adapt the graph by optimizing task-specific loss function using labelled data. These adaptations are made either via attention or by attenuating or enhancing various low-frequency/high-frequency signals, as needed for the task at hand. More recent approaches adapt the eigenvalues of the graph. One important interpretation of this adaptation is that these models select/weigh the eigenvectors of the graph. Based on this interpretation, we present an eigendecomposition based approach and propose EigenNetwork models that improve the performance of GNNs on heterophilic graphs. Performance improvement is achieved by learning flexible graph adaptation functions that modulate the eigenvalues of the graph. Regularization of these functions via parameter sharing helps to improve the performance even more. Our approach achieves up to 11% improvement in performance over the state-of-the-art methods on heterophilic graphs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Effective Polynomial Filter Adaptation for Graph Neural Networks
Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform poorly on heterophilic graphs, where con…
Node ClassificationGraph Domain Adaptation via Homophily-Agnostic Reconstructing Structure
Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs, addressing the challenge of label scarcity. However, existing GDA methods typically assume that both source and tar…
GRAPH DOMAIN ADAPTATIONLanguage Model-Enhanced Message Passing for Heterophilic Graph Learning
Traditional graph neural networks (GNNs), which rely on homophily-driven message passing, struggle with heterophilic graphs where connected nodes exhibit dissimilar features and different labels. While existing methods a…
Active LearningGraph LearningLanguage ModelingLanguage ModellingExploring the Potential of Large Language Models for Heterophilic Graphs
Large language models (LLMs) have presented significant opportunities to enhance various machine learning applications, including graph neural networks (GNNs). By leveraging the vast open-world knowledge within LLMs, we …
Node ClassificationWorld KnowledgeA Piece-wise Polynomial Filtering Approach for Graph Neural Networks
Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform poorly on heterophilic graphs, where con…
Node Classification