Research map / Graph learning / Knowledge and temporal graphs
Heterogeneity-Aware Twitter Bot Detection with Relational Graph Transformers
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the heterogeneity-aware relational graph transformer and semantic attention framework instead of BotRGCN | Twitter bot detection · TwiBot-20 | Accuracy: 0.8462 -> 0.8664 | Helped |
| Add transformer attention to the relational graph transformer (ablation) | Ours · TwiBot-20 | Accuracy: 0.8521 -> 0.8664 | Helped |
| Add gated residual connections to the relational graph transformer (ablation) | Ours · TwiBot-20 | Accuracy: 0.8478 -> 0.8664 | Helped |
| Use relational graph transformers instead of GAT (ablation) | Ours · TwiBot-20 | Accuracy: 0.8571 -> 0.8664 | Helped |
| Use relational graph transformers instead of GCN (ablation) | Ours · TwiBot-20 | Accuracy: 0.8444 -> 0.8664 | Helped |
| Use relational graph transformers instead of SAGE (ablation) | Ours · TwiBot-20 | Accuracy: 0.8546 -> 0.8664 | Helped |
| Use semantic attention instead of summation to aggregate relations (ablation) | Ours · TwiBot-20 | Accuracy: 0.8512 -> 0.8664 | Helped |
| Use semantic attention instead of mean pooling to aggregate relations (ablation) | Ours · TwiBot-20 | Accuracy: 0.8512 -> 0.8664 | Helped |
| Use semantic attention instead of max pooling to aggregate relations (ablation) | Ours · TwiBot-20 | Accuracy: 0.8495 -> 0.8664 | Helped |
| Use semantic attention instead of min pooling to aggregate relations (ablation) | Ours · TwiBot-20 | Accuracy: 0.8555 -> 0.8664 | Helped |
| Include both follower and following edges rather than a reduced edge set (ablation) | Ours · TwiBot-20 | Accuracy | Helped |
| Model heterogeneous relations rather than using a homogeneous relation setting (ablation) | Ours · TwiBot-20 | Accuracy | Helped |
Closest papers by meaning
- Adversarial Socialbots Modeling Based on Structural Information Principles (AAAI 2024 · similarity 0.84)
- SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter (AAAI 2024 · similarity 0.83)
- Learning Complex Heterogeneous Multimodal Fake News via Social Latent Network Inference (AAAI 2025 · similarity 0.83)
- HeterSEED: Semantics–Structure Decoupling for Heterogeneous Graph Learning under Heterophily (NeurIPS 2026 · similarity 0.82)
- Partitioning Message Passing for Graph Fraud Detection (ICLR 2024 · similarity 0.82)
- DAG-Aware Variational Autoencoder for Social Propagation Graph Generation (AAAI 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.