Research map / Graph learning / Graph self-supervised learning
Multi-dimensional Adaptive Mix-hop Contextual Learning Framework for Universal Graph Anomaly Detection
Zhaowei Liu, Leilei Jiang, Haitao Yang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| SAARCS vs runner-up baselines | SAARCS · 8 GAD datasets | AUROC: best on 6/8; AD-GCL 92.37 vs 90.77 on Cora, ADA-GAD 98.44 vs 93.15 on Weibo | Mixed |
| replace composite spatial feature alignment with random projection (ablation) | SAARCS · 8 GAD datasets | AUROC: 2%-15% drop when removed | Improved |
| add adaptive multi-hop (vs fixed hop) residual encoder (ablation) | SAARCS · 8 GAD datasets | AUROC: average 5% AUROC reduction when fixed | Improved |
| add residual graph encoder (vs GCN) (ablation) | SAARCS · 8 GAD datasets | AUROC | Improved |
| add cross-node contextual attention reconstruction scoring (vs binary classification) (ablation) | SAARCS · 8 GAD datasets | AUROC: 2%-8% degradation when removed | Improved |
| vary hop count 1 to 5 (ablation) | SAARCS · Cora, Amazon | AUROC: peak h=3 (Cora), h=4 (Amazon) | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ADA-GAD — ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection (AAAI 2024) · better on 7 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- ARC: A Generalist Graph Anomaly Detector with In-Context Learning (NeurIPS 2024 · similarity 0.92)
- UniGAD: Unifying Multi-level Graph Anomaly Detection (NeurIPS 2024 · similarity 0.89)
- UniFORM: Towards Unified Framework for Anomaly Detection on Graphs (AAAI 2025 · similarity 0.89)
- DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector (ICLR 2025 · similarity 0.89)
- Graph Anomaly Detection as Dynamical Transport: Training-Free Scoring via Empirical Bayes (NeurIPS 2026 · similarity 0.89)
- ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection (AAAI 2024 · similarity 0.88)
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.
