Papers › Beyond Low-frequency Information in Graph Convolutional Networks

Beyond Low-frequency Information in Graph Convolutional Networks

4 Jan 2021arXiv:2101.00797archive 2025-07-28

Deyu Bo, Xiao Wang, Chuan Shi, HuaWei Shen

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bdy9527/FAGCN officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Node ClassificationNode Classification on Non-Homophilic (Heterophilic) Graphs

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Classification Actor FAGCN Accuracy 34.82 ± 1.35 #48 of 62 Archive leaderboard report
Node Classification Chameleon FAGCN Accuracy 46.07 ± 2.11 #60 of 61 Archive leaderboard report
Node Classification Chameleon (60%/20%/20% random splits) FAGCN 1:1 Accuracy 49.47 ± 2.84 #36 of 38 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) FAGCN 1:1 Accuracy 82.37 ± 1.46 #2 of 33 Archive leaderboard report
Node Classification CiteSeer (60%/20%/20% random splits) H2GCN 1:1 Accuracy 79.97 ± 0.69 #23 of 33 Archive leaderboard report
Node Classification Citeseer (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 77.07 ± 2.05 #14 of 26 Archive leaderboard report
Node Classification Cora (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 88.05 ± 1.57 #10 of 26 Archive leaderboard report
Node Classification Cora (60%/20%/20% random splits) FAGCN 1:1 Accuracy 88.85 ± 1.36 #16 of 33 Archive leaderboard report
Node Classification Cornell FAGCN Accuracy 76.76 ± 5.87 #46 of 60 Archive leaderboard report
Node Classification Cornell (60%/20%/20% random splits) FAGCN 1:1 Accuracy 88.03 ± 5.6 #21 of 36 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) H2GCN 1:1 Accuracy 38.85 ± 1.17 #23 of 37 Archive leaderboard report
Node Classification Film (60%/20%/20% random splits) FAGCN 1:1 Accuracy 31.59 ± 1.37 #35 of 37 Archive leaderboard report
Node Classification PubMed (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 88.09 ± 1.38 #22 of 26 Archive leaderboard report
Node Classification PubMed (60%/20%/20% random splits) FAGCN 1:1 Accuracy 89.98 ± 0.54 #18 of 37 Archive leaderboard report
Node Classification Squirrel FAGCN Accuracy 30.83 ± 0.69 #58 of 59 Archive leaderboard report
Node Classification Squirrel (60%/20%/20% random splits) FAGCN 1:1 Accuracy 42.24 ± 1.2 #25 of 37 Archive leaderboard report
Node Classification Texas FAGCN Accuracy 76.49 ± 2.87 #53 of 62 Archive leaderboard report
Node Classification Texas (60%/20%/20% random splits) FAGCN 1:1 Accuracy 88.85 ± 4.39 #19 of 36 Archive leaderboard report
Node Classification Wisconsin WRGAT Accuracy 86.98 ± 3.78 #32 of 63 Archive leaderboard report
Node Classification Wisconsin FAGCN Accuracy 79.61 ± 1.58 #53 of 63 Archive leaderboard report
Node Classification Wisconsin (60%/20%/20% random splits) FAGCN 1:1 Accuracy 89.75 ± 6.37 #18 of 35 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 46.07 ± 2.11 #29 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Chameleon(60%/20%/20% random splits) FAGCN 1:1 Accuracy 49.47 ± 2.84 #30 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 76.76 ± 5.87 #23 of 27 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Cornell (60%/20%/20% random splits) FAGCN 1:1 Accuracy 88.03 ± 5.6 #21 of 33 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Deezer-Europe FAGCN 1:1 Accuracy 66.86±0.53 #10 of 28 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Film(48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 34.82 ± 1.35 #22 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Squirrel (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 30.83 ± 0.69 #29 of 29 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) H2GCN 1:1 Accuracy 84.86 ± 7.23 #10 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 76.49 ± 2.87 #22 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Texas(60%/20%/20% random splits) FAGCN 1:1 Accuracy 88.85 ± 4.39 #18 of 32 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin (48%/32%/20% fixed splits) FAGCN 1:1 Accuracy 79.61 ± 1.58 #21 of 26 Archive leaderboard report
Node Classification on Non-Homophilic (Heterophilic) Graphs Wisconsin(60%/20%/20% random splits) FAGCN 1:1 Accuracy 89.75 ± 6.37 #18 of 32 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Graph Convolutional Networks

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections