# Spectral Clustering of Attributed Multi-relational Graphs

arXiv: https://arxiv.org/abs/2311.01840 · HTML: https://mlsanity.com/paper/2311.01840/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 45 references that are in the map.
- First posted on arXiv 3 Nov 2023.

## Builds on (most cited first, 6 of 6)

- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Heterogeneous Graph Attention Network](https://mlsanity.com/paper/1903.07293/) (2019)
- [Unsupervised Attributed Multiplex Network Embedding](https://mlsanity.com/paper/1911.06750/) (2019)
- [Community Detection in Networks with Node Attributes](https://mlsanity.com/paper/1401.7267/) (2014)
- [Unsupervised Differentiable Multi-aspect Network Embedding](https://mlsanity.com/paper/2006.04239/) (2020)
- [Multilayer Spectral Graph Clustering via Convex Layer Aggregation: Theory and Algorithms](https://mlsanity.com/paper/1708.02620/) (2017)

## Built on by (most cited first, 2 of 2)

- [A Novel Normalized-Cut Solver with Nearest Neighbor Hierarchical Initialization](https://mlsanity.com/paper/2311.15214/) (2023)
- [Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering](https://mlsanity.com/paper/2603.20829/) (2026)

## Abstract (arXiv)

Graph clustering aims at discovering a natural grouping of the nodes such that similar nodes are assigned to a common cluster. Many different algorithms have been proposed in the literature: for simple graphs, for graphs with attributes associated to nodes, and for graphs where edges represent different types of relations among nodes. However, complex data in many domains can be represented as both attributed and multi-relational networks. In this paper, we propose SpectralMix, a joint dimensionality reduction technique for multi-relational graphs with categorical node attributes. SpectralMix integrates all information available from the attributes, the different types of relations, and the graph structure to enable a sound interpretation of the clustering results. Moreover, it generalizes existing techniques: it reduces to spectral embedding and clustering when only applied to a single graph and to homogeneity analysis when applied to categorical data. Experiments conducted on several real-world datasets enable us to detect dependencies between graph structure and categorical attributes, moreover, they exhibit the superiority of SpectralMix over existing methods.