# mGNN: Generalizing the Graph Neural Networks to the Multilayer Case

arXiv: https://arxiv.org/abs/2109.10119 · HTML: https://mlsanity.com/paper/2109.10119/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 60 references that are in the map.
- First posted on arXiv 21 Sep 2021.

## Builds on (most cited first, 25 of 25)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Graph Convolutional Neural Networks for Web-Scale Recommender Systems](https://mlsanity.com/paper/1806.01973/) (2018)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Representation Learning on Graphs: Methods and Applications](https://mlsanity.com/paper/1709.05584/) (2017)
- [Modeling polypharmacy side effects with graph convolutional networks](https://mlsanity.com/paper/1802.00543/) (2018)
- [Multilayer Networks](https://mlsanity.com/paper/1309.7233/) (2013)
- [Chip Placement with Deep Reinforcement Learning](https://mlsanity.com/paper/2004.10746/) (2020)
- [The structure and dynamics of multilayer networks](https://mlsanity.com/paper/1407.0742/) (2014)
- [Layer aggregation and reducibility of multilayer interconnected networks](https://mlsanity.com/paper/1405.0425/) (2014)
- [Random walks and diffusion on networks](https://mlsanity.com/paper/1612.03281/) (2016)
- [Utilising Graph Machine Learning within Drug Discovery and Development](https://mlsanity.com/paper/2012.05716/) (2020)
- [Multi-GCN: Graph Convolutional Networks for Multi-View Networks, with Applications to Global Poverty](https://mlsanity.com/paper/1901.11213/) (2019)
- [Machine learning dismantling and early-warning signals of disintegration in complex systems](https://mlsanity.com/paper/2101.02453/) (2021)
- [Random Walks on Multiplex Networks](https://mlsanity.com/paper/1306.0519/) (2013)
- [Spectral properties of the Laplacian of multiplex networks](https://mlsanity.com/paper/1307.2090/) (2013)
- [Eigenvector centrality of nodes in multiplex networks](https://mlsanity.com/paper/1305.7445/) (2013)
- [Structural measures for multiplex networks](https://mlsanity.com/paper/1308.3182/) (2013)
- [Evolutionary games on multilayer networks: A colloquium](https://mlsanity.com/paper/1504.04359/) (2015)
- [Centrality in Interconnected Multilayer Networks](https://mlsanity.com/paper/1311.2906/) (2013)
- [Measuring and modelling correlations in multiplex networks](https://mlsanity.com/paper/1403.1546/) (2014)
- [Communicability reveals a transition to coordinated behavior in multiplex networks](https://mlsanity.com/paper/1312.3234/) (2013)
- [Deep Learning Super-Diffusion in Multiplex Networks](https://mlsanity.com/paper/1811.04104/) (2018)

## Built on by (most cited first, 4 of 4)

- [Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction](https://mlsanity.com/paper/2402.00299/) (2024)
- [PAHD: Perception-Action based Human Decision Making using Explainable Graph Neural Networks on SAR Images](https://mlsanity.com/paper/2401.02687/) (2024)
- [Learning the Right Layers: a Data-Driven Layer-Aggregation Strategy for Semi-Supervised Learning on Multilayer Graphs](https://mlsanity.com/paper/2306.00152/) (2023)
- [Multilayer GNN for Predictive Maintenance and Clustering in Power Grids](https://mlsanity.com/paper/2507.07298/) (2025)

## Abstract (arXiv)

Networks are a powerful tool to model complex systems, and the definition of many Graph Neural Networks (GNN), Deep Learning algorithms that can handle networks, has opened a new way to approach many real-world problems that would be hardly or even untractable. In this paper, we propose mGNN, a framework meant to generalize GNNs to the case of multi-layer networks, i.e., networks that can model multiple kinds of interactions and relations between nodes. Our approach is general (i.e., not task specific) and has the advantage of extending any type of GNN without any computational overhead. We test the framework into three different tasks (node and network classification, link prediction) to validate it.