Papers › Mutual Information Maximization in Graph Neural Networks

Mutual Information Maximization in Graph Neural Networks

21 May 2019arXiv:1905.08509archive 2025-07-28

Xinhan Di, Pengqian Yu, Rui Bu, Mingchao Sun

A variety of graph neural networks (GNNs) frameworks for representation learning on graphs have been recently developed. These frameworks rely on aggregation and iteration scheme to learn the representation of nodes. However, information between nodes is inevitably lost in the scheme during learning. In order to reduce the loss, we extend the GNNs frameworks by exploring the aggregation and iteration scheme in the methodology of mutual information. We propose a new approach of enlarging the normal neighborhood in the aggregation of GNNs, which aims at maximizing mutual information. Based on a series of experiments conducted on several benchmark datasets, we show that the proposed approach improves the state-of-the-art performance for four types of graph tasks, including supervised and semi-supervised graph classification, graph link prediction and graph edge generation and classification.

PaperPDFCode

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

Code

CODE-SUBMIT/Graph_Neighborhood_1 officialmentioned in paperpytorch 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 ClassificationGraph ClassificationGraph Neural NetworkLink PredictionRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification 20NEWS sKNN-LDS Accuracy 47.9 #1 of 1 Archive leaderboard report
Graph Classification COLLAB sGIN Accuracy 80.71% #10 of 39 Archive leaderboard report
Graph Classification Cancer sKNN-LDS Accuracy 95.7 #1 of 1 Archive leaderboard report
Graph Classification Citeseer sKNN-LDS Accuracy 73.7 #1 of 1 Archive leaderboard report
Graph Classification Cora sKNN-LDS Accuracy 72.3 #1 of 1 Archive leaderboard report
Graph Classification Digits sKNN-LDS Accuracy 92.5 #1 of 1 Archive leaderboard report
Graph Classification IMDb-B sGIN Accuracy 77.94% #14 of 51 Archive leaderboard report
Graph Classification IMDb-M sGIN Accuracy 54.52% #7 of 36 Archive leaderboard report
Graph Classification MUTAG sGIN Accuracy 94.14% #8 of 74 Archive leaderboard report
Graph Classification NCI1 sGIN Accuracy 83.85% #24 of 69 Archive leaderboard report
Graph Classification PROTEINS sGIN Accuracy 78.97% #13 of 103 Archive leaderboard report
Graph Classification PTC sGIN Accuracy 73.56% #6 of 37 Archive leaderboard report
Graph Classification Wine sKNN-LDS Accuracy 98 #1 of 1 Archive leaderboard report
Link Prediction Pubmed sGraphite-VAE AP 96.3% #9 of 13 Archive leaderboard report
Link Prediction Pubmed sGraphite-VAE AUC 94.8% #9 of 13 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.

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