Beyond Low-frequency Information in Graph Convolutional Networks
arXiv:2101.00797
Abstract
Graph neural networks (GNNs) have been proven to be effective in various network-related tasks. Most existing GNNs usually exploit the low-frequency signals of node features, which gives rise to one fundamental question: is the low-frequency information all we need in the real world applications? In this paper, we first present an experimental investigation assessing the roles of low-frequency and high-frequency signals, where the results clearly show that exploring low-frequency signal only is distant from learning an effective node representation in different scenarios. How can we adaptively learn more information beyond low-frequency information in GNNs? A well-informed answer can help GNNs enhance the adaptability. We tackle this challenge and propose a novel Frequency Adaptation Graph Convolutional Networks (FAGCN) with a self-gating mechanism, which can adaptively integrate different signals in the process of message passing. For a deeper understanding, we theoretically analyze the roles of low-frequency signals and high-frequency signals on learning node representations, which further explains why FAGCN can perform well on different types of networks. Extensive experiments on six real-world networks validate that FAGCN not only alleviates the over-smoothing problem, but also has advantages over the state-of-the-arts.
Accepted by AAAI 2021
Cited by in corpus (9)
- Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
- Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration
- Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
- Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
- Generalizing Graph Neural Networks on Out-Of-Distribution Graphs
- Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
- Label-Wise Graph Convolutional Network for Heterophilic Graphs
- Graph Neural Networks with Feature and Structure Aware Random Walk
- Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks