Papers › Graph Transformer Networks

Graph Transformer Networks

6 Nov 2019NeurIPS 2019 12arXiv:1911.06455archive 2025-07-28

Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim

Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion. Graph Transformer layer, a core layer of GTNs, learns a soft selection of edge types and composite relations for generating useful multi-hop connections so-called meta-paths. Our experiments show that GTNs learn new graph structures, based on data and tasks without domain knowledge, and yield powerful node representation via convolution on the new graphs. Without domain-specific graph preprocessing, GTNs achieved the best performance in all three benchmark node classification tasks against the state-of-the-art methods that require pre-defined meta-paths from domain knowledge.

Paper PDF Conference PDF Code

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

Code

seongjunyun/Graph_Transformer_Networks officialmentioned in papermentioned on GitHubpytorch 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

General Classification Heterogeneous Node Classification Link Prediction Node Classification Representation Learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Heterogeneous Node Classification	ACM (Heterogeneous Node Classification)	GTN	Macro-F1	91.31	#7 of 11	Archive leaderboard	report
Heterogeneous Node Classification	ACM (Heterogeneous Node Classification)	GTN	Micro-F1	91.20	#7 of 11	Archive leaderboard	report
Heterogeneous Node Classification	DBLP (Heterogeneous Node Classification)	GTN	Macro-F1	93.52	#5 of 11	Archive leaderboard	report
Heterogeneous Node Classification	DBLP (Heterogeneous Node Classification)	GTN	Micro-F1	93.97	#5 of 11	Archive leaderboard	report
Heterogeneous Node Classification	IMDB (Heterogeneous Node Classification)	GTN	Macro-F1	60.47	#6 of 11	Archive leaderboard	report
Heterogeneous Node Classification	IMDB (Heterogeneous Node Classification)	GTN	Micro-F1	65.14	#6 of 11	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

Absolute Position Encodings Adam Attention BPE Convolution Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer ReLU Residual Connection Softmax Transformer

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