Papers › GTNet: A Tree-Based Deep Graph Learning Architecture

GTNet: A Tree-Based Deep Graph Learning Architecture

27 Apr 2022arXiv:2204.12802archive 2025-07-28

Nan Wu, Chaofan Wang

We propose Graph Tree Networks (GTNets), a deep graph learning architecture with a new general message passing scheme that originates from the tree representation of graphs. In the tree representation, messages propagate upward from the leaf nodes to the root node, and each node preserves its initial information prior to receiving information from its child nodes (neighbors). We formulate a general propagation rule following the nature of message passing in the tree to update a node's feature by aggregating its initial feature and its neighbor nodes' updated features. Two graph representation learning models are proposed within this GTNet architecture - Graph Tree Attention Network (GTAN) and Graph Tree Convolution Network (GTCN), with experimentally demonstrated state-of-the-art performance on several popular benchmark datasets. Unlike the vanilla Graph Attention Network (GAT) and Graph Convolution Network (GCN) which have the "over-smoothing" issue, the proposed GTAN and GTCN models can go deep as demonstrated by comprehensive experiments and rigorous theoretical analysis.

PaperPDFCode

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

Code

nanw16/GTNet 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

Graph AttentionGraph LearningGraph Representation LearningRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Node Property Prediction ogbn-arxiv GTAN Ext. data No #52 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GTAN Number of params 39208 #52 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GTAN Test Accuracy 0.7297 ± 0.0017 #52 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GTAN Validation Accuracy 0.7384 ± 0.0007 #52 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GTCN Ext. data No #62 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GTCN Number of params 109096 #62 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GTCN Test Accuracy 0.7225 ± 0.0017 #62 of 86 Archive leaderboard report
Node Property Prediction ogbn-arxiv GTCN Validation Accuracy 0.7320 ± 0.0005 #62 of 86 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

Convolution

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