Papers › An End-to-End Deep Learning Architecture for Graph Classification

An End-to-End Deep Learning Architecture for Graph Classification

29 Apr 2018AAAI-18 2018 4archive 2025-07-28

Muhan Zhang, Zhicheng Cui, Marion Neumann, Yixin Chen

Neural networks are typically designed to deal with data in tensor forms. In this paper, we propose a novel neural network architecture accepting graphs of arbitrary structure. Given a dataset containing graphs in the form of (G,y) where G is a graph and y is its class, we aim to develop neural networks that read the graphs directly and learn a classification function. There are two main challenges: 1) how to extract useful features characterizing the rich information encoded in a graph for classification purpose, and 2) how to sequentially read a graph in a meaningful and consistent order. To address the first challenge, we design a localized graph convolution model and show its connection with two graph kernels. To address the second challenge, we design a novel SortPooling layer which sorts graph vertices in a consistent order so that traditional neural networks can be trained on the graphs. Experiments on benchmark graph classification datasets demonstrate that the proposed architecture achieves highly competitive performance with state-of-the-art graph kernels and other graph neural network methods. Moreover, the architecture allows end-to-end gradient-based training with original graphs, without the need to first transform graphs into vectors.

PaperPDFCode

Code

muhanzhang/DGCNN mentioned in papertorch 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

Deep LearningGeneral ClassificationGraph ClassificationGraph Neural Network

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification COLLAB DGCNN Accuracy 73.76% #27 of 39 Archive leaderboard report
Graph Classification COLLAB DGCNN (sum) Accuracy 69.45% #33 of 39 Archive leaderboard report
Graph Classification D&D DGCNN Accuracy 79.37% #18 of 53 Archive leaderboard report
Graph Classification D&D DGCNN (sum) Accuracy 78.72% #22 of 53 Archive leaderboard report
Graph Classification IMDb-B DGCNN Accuracy 70.03% #46 of 51 Archive leaderboard report
Graph Classification IMDb-B DGCNN (sum) Accuracy 51.69% #50 of 51 Archive leaderboard report
Graph Classification IMDb-M DGCNN Accuracy 47.83% #31 of 36 Archive leaderboard report
Graph Classification IMDb-M DGCNN (sum) Accuracy 42.76% #35 of 36 Archive leaderboard report
Graph Classification MUTAG DGCNN Accuracy 85.83% #59 of 74 Archive leaderboard report
Graph Classification NCI1 DGCNN (sum) Accuracy 69.00% #63 of 69 Archive leaderboard report
Graph Classification PROTEINS DGCNN Accuracy 76.26% #54 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.

Methods

ConvolutionDGCNN

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