RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search
arXiv:2206.06757 · doi:10.1145/3572403
Abstract
Social bots are referred to as the automated accounts on social networks that make attempts to behave like human. While Graph Neural Networks (GNNs) has been massively applied to the field of social bot detection, a huge amount of domain expertise and prior knowledge is heavily engaged in the state-of-the art approaches to design a dedicated neural network architecture for a specific classification task. Involving oversized nodes and network layers in the model design, however, usually causes the over-smoothing problem and the lack of embedding discrimination. In this paper, we propose RoSGAS, a novel Reinforced and Self-supervised GNN Architecture Search framework to adaptively pinpoint the most suitable multi-hop neighborhood and the number of layers in the GNN architecture. More specifically, we consider the social bot detection problem as a user-centric subgraph embedding and classification task. We exploit heterogeneous information network to present the user connectivity by leveraging account metadata, relationships, behavioral features and content features. RoSGAS uses a multi-agent deep reinforcement learning (RL) mechanism for navigating the search of optimal neighborhood and network layers to learn individually the subgraph embedding for each target user. A nearest neighbor mechanism is developed for accelerating the RL training process, and RoSGAS can learn more discriminative subgraph embedding with the aid of self-supervised learning. Experiments on 5 Twitter datasets show that RoSGAS outperforms the state-of-the-art approaches in terms of accuracy, training efficiency and stability, and has better generalization when handling unseen samples.
arXiv comment32 pages, 12 figures accpted by ACM Transactions on the Web (TWEB)
References in corpus (22)
- Emergence of scaling in random networks
- LINE: Large-scale Information Network Embedding
- The Rise of Social Bots
- Simplifying Graph Convolutional Networks
- Representation Learning on Graphs with Jumping Knowledge Networks
- Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters
- Fame for sale: efficient detection of fake Twitter followers
- Graph Neural Networks with convolutional ARMA filters
- Arming the public with artificial intelligence to counter social bots
- Scalable and Generalizable Social Bot Detection through Data Selection
- GraphSAINT: Graph Sampling Based Inductive Learning Method
- A Decade of Social Bot Detection
- Online Human-Bot Interactions: Detection, Estimation, and Characterization
- Origins of power-law degree distribution in the heterogeneity of human activity in social networks
- TwiBot-20: A Comprehensive Twitter Bot Detection Benchmark
- Dissecting a Social Botnet: Growth, Content and Influence in Twitter
- Auto-GNN: Neural Architecture Search of Graph Neural Networks
- Subgraph Neural Networks
- RTbust: Exploiting Temporal Patterns for Botnet Detection on Twitter
- Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
- Heterogeneity-aware Twitter Bot Detection with Relational Graph Transformers
- HAWK: Rapid Android Malware Detection through Heterogeneous Graph Attention Networks