# Exchangeable Random Measures for Sparse and Modular Graphs with Overlapping Communities

arXiv: https://arxiv.org/abs/1602.02114 · HTML: https://mlsanity.com/paper/1602.02114/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Feb 2016.

## Built on by (most cited first, 8 of 8)

- [EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model](https://mlsanity.com/paper/2208.06322/) (2022)
- [Poisson Hierarchical Indian Buffet Processes-With Indications for Microbiome Species Sampling Models](https://mlsanity.com/paper/2502.01919/) (2025)
- [Latent structure blockmodels for Bayesian spectral graph clustering](https://mlsanity.com/paper/2107.01734/) (2021)
- [Spectral embedding and the latent geometry of multipartite networks](https://mlsanity.com/paper/2202.03945/) (2022)
- [A Survey on Machine Learning Solutions for Graph Pattern Extraction](https://mlsanity.com/paper/2204.01057/) (2022)
- [Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN](https://mlsanity.com/paper/2210.11174/) (2022)
- [A Local Perspective-based Model for Overlapping Community Detection](https://mlsanity.com/paper/2503.21558/) (2025)
- [Rapidly Varying Completely Random Measures for Modeling Extremely Sparse Networks](https://mlsanity.com/paper/2505.13206/) (2025)

## Abstract (arXiv)

We propose a novel statistical model for sparse networks with overlapping community structure. The model is based on representing the graph as an exchangeable point process, and naturally generalizes existing probabilistic models with overlapping block-structure to the sparse regime. Our construction builds on vectors of completely random measures, and has interpretable parameters, each node being assigned a vector representing its level of affiliation to some latent communities. We develop methods for simulating this class of random graphs, as well as to perform posterior inference. We show that the proposed approach can recover interpretable structure from two real-world networks and can handle graphs with thousands of nodes and tens of thousands of edges.