Saved in:
Bibliographic Details
Main Authors: Chen, Sirry, Feng, Shuo, Liang, Songsong, Zong, Chen-Chen, Li, Jing, Li, Piji
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.10558
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916270537965568
author Chen, Sirry
Feng, Shuo
Liang, Songsong
Zong, Chen-Chen
Li, Jing
Li, Piji
author_facet Chen, Sirry
Feng, Shuo
Liang, Songsong
Zong, Chen-Chen
Li, Jing
Li, Piji
contents Social media bot detection is increasingly crucial with the rise of social media platforms. Existing methods predominantly construct social networks as graph and utilize graph neural networks (GNNs) for bot detection. However, most of these methods focus on how to improve the performance of GNNs while neglecting the community structure within social networks. Moreover, GNNs based methods still face problems such as poor model generalization due to the relatively small scale of the dataset and over-smoothness caused by information propagation mechanism. To address these problems, we propose a Community-Aware Heterogeneous Graph Contrastive Learning framework (CACL), which constructs social network as heterogeneous graph with multiple node types and edge types, and then utilizes community-aware module to dynamically mine both hard positive samples and hard negative samples for supervised graph contrastive learning with adaptive graph enhancement algorithms. Extensive experiments demonstrate that our framework addresses the previously mentioned challenges and outperforms competitive baselines on three social media bot benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10558
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection
Chen, Sirry
Feng, Shuo
Liang, Songsong
Zong, Chen-Chen
Li, Jing
Li, Piji
Social and Information Networks
Social media bot detection is increasingly crucial with the rise of social media platforms. Existing methods predominantly construct social networks as graph and utilize graph neural networks (GNNs) for bot detection. However, most of these methods focus on how to improve the performance of GNNs while neglecting the community structure within social networks. Moreover, GNNs based methods still face problems such as poor model generalization due to the relatively small scale of the dataset and over-smoothness caused by information propagation mechanism. To address these problems, we propose a Community-Aware Heterogeneous Graph Contrastive Learning framework (CACL), which constructs social network as heterogeneous graph with multiple node types and edge types, and then utilizes community-aware module to dynamically mine both hard positive samples and hard negative samples for supervised graph contrastive learning with adaptive graph enhancement algorithms. Extensive experiments demonstrate that our framework addresses the previously mentioned challenges and outperforms competitive baselines on three social media bot benchmarks.
title CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection
topic Social and Information Networks
url https://arxiv.org/abs/2405.10558