Papers › Multi-Mask Aggregators for Graph Neural Networks

Multi-Mask Aggregators for Graph Neural Networks

24 Nov 2022Learning on Graphs Conference 2022 11archive 2025-07-28

Ahmet Sarıgün, Ahmet Sureyya Rifaioglu

One of the most critical operations in graph neural networks (GNNs) is the aggregation operation, which aims to extract information from neighbors of the target node. Several convolution methods have been proposed such as standard graph convolution (GCN), graph attention (GAT), and message passing (MPNN). In this study, we propose an aggregation method called Multi-Mask Aggregators (MMA), where the model learns a weighted mask for each aggregator before collecting neighboring messages. MMA draws similarities with the GAT and MPNN but has some theoretical and practical advantages. Intuitively, our framework is not limited by the number of heads from GAT and has more discriminative than an MPNN. The performance of MMA was compared with the well-known baseline methods in both node classification and graph regression tasks on widely-used benchmarking datasets, and it has shown improved performance. Dataset and codes are available at https://github.com/asarigun/mma.

PaperPDFCode

Code

asarigun/mma officialmentioned in paperpytorch 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

BenchmarkingGraph RegressionNode Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Graph Regression ZINC MMA MAE 0.156 #23 of 27 Archive leaderboard report
Node Classification Citeseer MMA Accuracy 76.30% #13 of 71 Archive leaderboard report
Node Classification Cora MMA Accuracy 85.80% #21 of 73 Archive leaderboard report
Node Classification Pubmed MMA Accuracy 86.00% #22 of 70 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

ConvolutionGATMPNN

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