Papers › Graph Capsule Convolutional Neural Networks

Graph Capsule Convolutional Neural Networks

21 May 2018arXiv:1805.08090archive 2025-07-28

Saurabh Verma, Zhi-Li Zhang

Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision. In this paper, we expose and tackle some of the basic weaknesses of a GCNN model with a capsule idea presented in \cite{hinton2011transforming} and propose our Graph Capsule Network (GCAPS-CNN) model. In addition, we design our GCAPS-CNN model to solve especially graph classification problem which current GCNN models find challenging. Through extensive experiments, we show that our proposed Graph Capsule Network can significantly outperforms both the existing state-of-art deep learning methods and graph kernels on graph classification benchmark datasets.

PaperPDFCode

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

Code

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

Deep LearningGeneral ClassificationGraph Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification D&D GCAPS-CNN Accuracy 77.62% #31 of 53 Archive leaderboard report
Graph Classification IMDb-B GCAPS-CNN Accuracy 71.69% #42 of 51 Archive leaderboard report
Graph Classification NCI1 GCAPS-CNN Accuracy 82.72% #29 of 69 Archive leaderboard report
Graph Classification PROTEINS GCAPS-CNN Accuracy 76.40% #47 of 103 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