Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2010.15727 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911974792626176 |
|---|---|
| author | Wang, Yueqi Lee, Yoonho Basu, Pallab Lee, Juho Teh, Yee Whye Paninski, Liam Pakman, Ari |
| author_facet | Wang, Yueqi Lee, Yoonho Basu, Pallab Lee, Juho Teh, Yee Whye Paninski, Liam Pakman, Ari |
| contents | Learning community structures in graphs has broad applications across scientific domains. While graph neural networks (GNNs) have been successful in encoding graph structures, existing GNN-based methods for community detection are limited by requiring knowledge of the number of communities in advance, in addition to lacking a proper probabilistic formulation to handle uncertainty. We propose a simple framework for amortized community detection, which addresses both of these issues by combining the expressive power of GNNs with recent methods for amortized clustering. Our models consist of a graph representation backbone that extracts structural information and an amortized clustering network that naturally handles variable numbers of clusters. Both components combine into well-defined models of the posterior distribution of graph communities and are jointly optimized given labeled graphs. At inference time, the models yield parallel samples from the posterior of community labels, quantifying uncertainty in a principled way. We evaluate several models from our framework on synthetic and real datasets, and demonstrate improved performance compared to previous methods. As a separate contribution, we extend recent amortized probabilistic clustering architectures by adding attention modules, which yield further improvements on community detection tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2010_15727 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Amortized Probabilistic Detection of Communities in Graphs Wang, Yueqi Lee, Yoonho Basu, Pallab Lee, Juho Teh, Yee Whye Paninski, Liam Pakman, Ari Machine Learning Learning community structures in graphs has broad applications across scientific domains. While graph neural networks (GNNs) have been successful in encoding graph structures, existing GNN-based methods for community detection are limited by requiring knowledge of the number of communities in advance, in addition to lacking a proper probabilistic formulation to handle uncertainty. We propose a simple framework for amortized community detection, which addresses both of these issues by combining the expressive power of GNNs with recent methods for amortized clustering. Our models consist of a graph representation backbone that extracts structural information and an amortized clustering network that naturally handles variable numbers of clusters. Both components combine into well-defined models of the posterior distribution of graph communities and are jointly optimized given labeled graphs. At inference time, the models yield parallel samples from the posterior of community labels, quantifying uncertainty in a principled way. We evaluate several models from our framework on synthetic and real datasets, and demonstrate improved performance compared to previous methods. As a separate contribution, we extend recent amortized probabilistic clustering architectures by adding attention modules, which yield further improvements on community detection tasks. |
| title | Amortized Probabilistic Detection of Communities in Graphs |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2010.15727 |