Papers › A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks

A Non-Negative Factorization approach to node pooling in Graph Convolutional Neural Networks

7 Sep 2019arXiv:1909.03287archive 2025-07-28

Davide Bacciu, Luigi Di Sotto

The paper discusses a pooling mechanism to induce subsampling in graph structured data and introduces it as a component of a graph convolutional neural network. The pooling mechanism builds on the Non-Negative Matrix Factorization (NMF) of a matrix representing node adjacency and node similarity as adaptively obtained through the vertices embedding learned by the model. Such mechanism is applied to obtain an incrementally coarser graph where nodes are adaptively pooled into communities based on the outcomes of the non-negative factorization. The empirical analysis on graph classification benchmarks shows how such coarsening process yields significant improvements in the predictive performance of the model with respect to its non-pooled counterpart.

PaperPDF

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

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 Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Classification COLLAB 1-NMFPool Accuracy 65.0% #38 of 39 Archive leaderboard report
Graph Classification D&D 1-NMFPool Accuracy 76.0% #41 of 53 Archive leaderboard report
Graph Classification ENZYMES 1-NMFPool Accuracy 24.1% #53 of 54 Archive leaderboard report
Graph Classification NCI1 1-NMFPool Accuracy 66.2% #67 of 69 Archive leaderboard report
Graph Classification PROTEINS 1-NMFPool Accuracy 72.1% #95 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