Papers › Gaussian-Induced Convolution for Graphs

Gaussian-Induced Convolution for Graphs

11 Nov 2018arXiv:1811.04393archive 2025-07-28

Jiatao Jiang, Zhen Cui, Chunyan Xu, Jian Yang

Learning representation on graph plays a crucial role in numerous tasks of pattern recognition. Different from grid-shaped images/videos, on which local convolution kernels can be lattices, however, graphs are fully coordinate-free on vertices and edges. In this work, we propose a Gaussian-induced convolution (GIC) framework to conduct local convolution filtering on irregular graphs. Specifically, an edge-induced Gaussian mixture model is designed to encode variations of subgraph region by integrating edge information into weighted Gaussian models, each of which implicitly characterizes one component of subgraph variations. In order to coarsen a graph, we derive a vertex-induced Gaussian mixture model to cluster vertices dynamically according to the connection of edges, which is approximately equivalent to the weighted graph cut. We conduct our multi-layer graph convolution network on several public datasets of graph classification. The extensive experiments demonstrate that our GIC is effective and can achieve the state-of-the-art results.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Graph ClassificationLearning Representation On Graph

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification ENZYMES GIC Accuracy 62.50% #26 of 54 Archive leaderboard report
Graph Classification MUTAG GIC Accuracy 94.44% #6 of 74 Archive leaderboard report
Graph Classification NCI1 GIC Accuracy 84.08% #23 of 69 Archive leaderboard report
Graph Classification NCI109 GIC Accuracy 82.86 #15 of 38 Archive leaderboard report
Graph Classification PROTEINS GIC Accuracy 77.65% #30 of 103 Archive leaderboard report
Graph Classification PTC GIC Accuracy 77.64% #3 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

Convolution

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