Beyond Low-frequency Information in Graph Convolutional Networks

By Deyu Bo, Xiao Wang, Chuan Shi, Huawei Shen. AAAI Conference on Artificial Intelligence, 2021

808 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/fbc136c8c81cd89206dc0fcb54e16bd98df83b62

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

Doina Precup

In Electrical and Electronic Engineering

Citations in the corpus

Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks (2021, methodology): “Most GCNs [2, 3] fail to effectively capture heterophily, so various designs have been proposed to handle it [10, 12, 14, 15].”
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods (2021, neutral): “Further, while new GNNs that work better in these non-homophilous settings have been developed [82, 44, 81, 17, 15, 73, 36, 35, 9, 54], their evaluation is limited to a few graph datasets used by Pei et al.”
Revisiting Heterophily For Graph Neural Networks (2022, methodology): “Non-local GNNs [28] propose a simple and effective non-local aggregation framework with an efficient attention-guided sorting for GNNs. FAGCN [4] learns edge-level aggregation weights as GAT [41] but allows the weights to be negative, which enables the network to capture high-frequency components in”
Finding Global Homophily in Graph Neural Networks When Meeting Heterophily (2022, neutral): “To generalize GNNs to heterophilous graphs, some recent works (Zhu et al., 2020b; Bo et al., 2021; Chien et al., 2020) have been proposed to leverage high-pass convolutional filters and multi-hop neighbors to address the heterophily issue.”
Language is All a Graph Needs (2023, methodology): “…(He et al., 2023), we select those top-ranked GNNs from the two corresponding benchmarks with 60%/20%/20% train/val/test splits, including Snowball, RevGAT, etc. (Abu-El-Haija et al., 2019; Pei et al., 2020; Wu et al., 2019; He et al., 2021; Bo et al., 2021; Chen et al., 2020b; Luan et al., 2022).”
Rethinking Graph Neural Networks for Anomaly Detection (2022, background): “Although the frequency responses of existing works (Wu et al., 2021; He et al., 2021; Bo et al., 2021) can cover nearly all frequency proﬁles, these GNNs with adaptive ﬁlters cannot guarantee to be band-pass and spectral-localized (Balcilar et al., 2020).”
A critical look at the evaluation of GNNs under heterophily: are we really making progress? (2023, methodology): “…use eight models designed for node classiﬁcation under het-erophily: H 2 GCN (Zhu et al., 2020), CPGNN (Zhu et al., 2021), GPR-GNN (Chien et al., 2021), FSGNN (Maurya et al., 2022), GloGNN (Li et al., 2022), FAGCN (Bo et al., 2021), GBK-8 GNN (Du et al., 2022), and JacobiConv (Wang & Zhang, 2022).”