# Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules

arXiv: https://arxiv.org/abs/1811.09595 · HTML: https://mlsanity.com/paper/1811.09595/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks](https://mlsanity.com/paper/2201.08932/) (2022)
- [Convolutional Filtering and Neural Networks with Non Commutative Algebras](https://mlsanity.com/paper/2108.09923/) (2021)
- [Beyond Sequence: Impact of Geometric Context for RNA Property Prediction](https://mlsanity.com/paper/2410.11933/) (2024)
- [Survey of Image Based Graph Neural Networks](https://mlsanity.com/paper/2106.06307/) (2021)
- [Reinforcement Learning For Data Poisoning on Graph Neural Networks](https://mlsanity.com/paper/2102.06800/) (2021)
- [Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA) for Remote Land-use Change Detection](https://mlsanity.com/paper/2303.14322/) (2023)
- [Revisiting 2D Convolutional Neural Networks for Graph-based Applications](https://mlsanity.com/paper/2105.11016/) (2021)
- [Fea2Fea: Exploring Structural Feature Correlations via Graph Neural Networks](https://mlsanity.com/paper/2106.13061/) (2021)
- [AMOSL: Adaptive Modality-wise Structure Learning in Multi-view Graph Neural Networks For Enhanced Unified Representation](https://mlsanity.com/paper/2406.02348/) (2024)

## Abstract (arXiv)

Spectral Graph Convolutional Networks (GCNs) are a generalization of convolutional networks to learning on graph-structured data. Applications of spectral GCNs have been successful, but limited to a few problems where the graph is fixed, such as shape correspondence and node classification. In this work, we address this limitation by revisiting a particular family of spectral graph networks, Chebyshev GCNs, showing its efficacy in solving graph classification tasks with a variable graph structure and size. Chebyshev GCNs restrict graphs to have at most one edge between any pair of nodes. To this end, we propose a novel multigraph network that learns from multi-relational graphs. We model learned edges with abstract meaning and experiment with different ways to fuse the representations extracted from annotated and learned edges, achieving competitive results on a variety of chemical classification benchmarks.