LGNov 29, 2024

Multigraph Message Passing with Bi-Directional Multi-Edge Aggregations

arXiv:2412.00241v21 citationsh-index: 2
Originality Incremental advance
AI Analysis

This addresses a specific bottleneck in graph learning for domains like fraud detection, though it appears incremental relative to existing multigraph GNNs.

The paper tackles the problem of applying Graph Neural Networks to multigraphs with parallel edges, proposing MEGA-GNN which introduces a two-stage aggregation process. The result shows it outperforms state-of-the-art solutions by up to 13% on Anti-Money Laundering datasets and matches accuracy on phishing classification datasets.

Graph Neural Networks (GNNs) have seen significant advances in recent years, yet their application to multigraphs, where parallel edges exist between the same pair of nodes, remains under-explored. Standard GNNs, designed for simple graphs, compute node representations by combining all connected edges at once, without distinguishing between edges from different neighbors. There are some GNN architectures proposed specifically for multigraphs, yet these architectures perform only node-level aggregation in their message passing layers, which limits their expressive power. Furthermore, these approaches either lack permutation equivariance when a strict total edge ordering is absent, or fail to preserve the topological structure of the multigraph. To address all these shortcomings, we propose MEGA-GNN, a unified framework for message passing on multigraphs that can effectively perform diverse graph learning tasks. Our approach introduces a two-stage aggregation process in the message passing layers: first, parallel edges are aggregated, followed by a node-level aggregation of messages from distinct neighbors. We show that MEGA-GNN is not only permutation equivariant but also universal given a strict total ordering on the edges. Experiments show that MEGA-GNN significantly outperforms state-of-the-art solutions by up to 13\% on Anti-Money Laundering datasets and is on par with their accuracy on real-world phishing classification datasets in terms of minority class F1 score.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes