Papers › Graph isomorphism UNet

Graph isomorphism UNet

23 Aug 2023Expert Systems with Applications 2023 8archive 2025-07-28

Alireza Amouzad, Zahra Dehghanian, Saeed Saravani, Maryam Amirmazlaghani, Behnam Roshanfekr

Graph embedding learning is a fundamental task when dealing with diverse datasets. While encoder–decoder architectures, such as U-Nets, have shown great success in image pixel-wise prediction tasks, applying similar methods to graph data poses challenges due to the lack of natural pooling and up-sampling operations for graphs. Recent methods leverage learnable parameters to extract structural information from neural networks and extend pooling and unpooling to graphs using node features and graph structural information. This paper proposes a novel model called GIUNet (Graph Isomorphism U-Net) for the graph classification task. The proposed Graph U-Net structure is based on graph isomorphism convolution while using a comprehensive pqPooling layer. The pqPooling layer in our approach effectively combines node features and graph structure information during the graph down-sampling stage. To incorporate graph structure information, we utilize both the spectral representation and node centrality measurements. Node centrality measurements capture various structural aspects of nodes in the graph, while the spectral representation helps us focus on the informative low-frequency components of the graph structure. Through ablation studies, we have demonstrated that leveraging the GIUNet model leads to significant improvements compared to state-of-the-art methods across multiple benchmark datasets.

PaperPDFCode

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

DecoderGraph ClassificationGraph Embedding

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification ENZYMES GIUNet Accuracy 70% #13 of 54 Archive leaderboard report
Graph Classification IMDb-B GIUNet Accuracy 76% #19 of 51 Archive leaderboard report
Graph Classification IMDb-M GIUNet Accuracy 54% #8 of 36 Archive leaderboard report
Graph Classification MUTAG GIUNet Accuracy 95.7% #4 of 74 Archive leaderboard report
Graph Classification NCI1 GIUNet Accuracy 80.2% #37 of 69 Archive leaderboard report
Graph Classification NCI109 GIUNet Accuracy 77 #24 of 38 Archive leaderboard report
Graph Classification PROTEINS GIUNet Accuracy 77.6% #31 of 103 Archive leaderboard report
Graph Classification PTC GIUNet Accuracy 85.7% #2 of 37 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

Concatenated Skip ConnectionConvolutionFocusMax PoolingReLUU-Net

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