Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Muttakin, Md Nurul, Hossain, Md Iqbal, Rahman, Md Saidur
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909327976038400
author Muttakin, Md Nurul
Hossain, Md Iqbal
Rahman, Md Saidur
author_facet Muttakin, Md Nurul
Hossain, Md Iqbal
Rahman, Md Saidur
contents Overlapping community detection is a key problem in graph mining. Some research has considered applying graph convolutional networks (GCN) to tackle the problem. However, it is still challenging to incorporate deep graph convolutional networks in the case of general irregular graphs. In this study, we design a deep dynamic residual graph convolutional network (DynaResGCN) based on our novel dynamic dilated aggregation mechanisms and a unified end-to-end encoder-decoder-based framework to detect overlapping communities in networks. The deep DynaResGCN model is used as the encoder, whereas we incorporate the Bernoulli-Poisson (BP) model as the decoder. Consequently, we apply our overlapping community detection framework in a research topics dataset without having ground truth, a set of networks from Facebook having a reliable (hand-labeled) ground truth, and in a set of very large co-authorship networks having empirical (not hand-labeled) ground truth. Our experimentation on these datasets shows significantly superior performance over many state-of-the-art methods for the detection of overlapping communities in networks.
format Preprint
id arxiv_https___arxiv_org_abs_2210_11174
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN
Muttakin, Md Nurul
Hossain, Md Iqbal
Rahman, Md Saidur
Artificial Intelligence
Overlapping community detection is a key problem in graph mining. Some research has considered applying graph convolutional networks (GCN) to tackle the problem. However, it is still challenging to incorporate deep graph convolutional networks in the case of general irregular graphs. In this study, we design a deep dynamic residual graph convolutional network (DynaResGCN) based on our novel dynamic dilated aggregation mechanisms and a unified end-to-end encoder-decoder-based framework to detect overlapping communities in networks. The deep DynaResGCN model is used as the encoder, whereas we incorporate the Bernoulli-Poisson (BP) model as the decoder. Consequently, we apply our overlapping community detection framework in a research topics dataset without having ground truth, a set of networks from Facebook having a reliable (hand-labeled) ground truth, and in a set of very large co-authorship networks having empirical (not hand-labeled) ground truth. Our experimentation on these datasets shows significantly superior performance over many state-of-the-art methods for the detection of overlapping communities in networks.
title Overlapping Community Detection using Dynamic Dilated Aggregation in Deep Residual GCN
topic Artificial Intelligence
url https://arxiv.org/abs/2210.11174