Papers with Code 아카이브
Graph Anomaly Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 2
- 보존된 평가 기록
- 2
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Polynomial Selection in Spectral Graph Neural Networks: An Error-Sum of Function Slices Approach
Temporal Graph Networks for Graph Anomaly Detection in Financial Networks
Generation is better than Modification: Combating High Class Homophily Variance in Graph Anomaly Detection
Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks
Towards Fair Graph Anomaly Detection: Problem, Benchmark Datasets, and Evaluation
FGAD: Self-boosted Knowledge Distillation for An Effective Federated Graph Anomaly Detection Framework
Generative Semi-supervised Graph Anomaly Detection
Alleviating Structural Distribution Shift in Graph Anomaly Detection
Multitask Active Learning for Graph Anomaly Detection
ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection
Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detection
Few-shot Message-Enhanced Contrastive Learning for Graph Anomaly Detection
Open-Set Graph Anomaly Detection via Normal Structure Regularisation
GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps
Towards Self-Interpretable Graph-Level Anomaly Detection
PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection
Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning
Class Label-aware Graph Anomaly Detection
Label-based Graph Augmentation with Metapath for Graph Anomaly Detection
Crowdsourcing Fraud Detection over Heterogeneous Temporal MMMA Graph
Graph Anomaly Detection at Group Level: A Topology Pattern Enhanced Unsupervised Approach
BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection
Coupled-Space Attacks against Random-Walk-based Anomaly Detection
GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection
Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation
GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction
Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection
MetaGAD: Meta Representation Adaptation for Few-Shot Graph Anomaly Detection
Energy Transformer
Graph Anomaly Detection in Time Series: A Survey
Subgraph Centralization: A Necessary Step for Graph Anomaly Detection
Mul-GAD: a semi-supervised graph anomaly detection framework via aggregating multi-view information
Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment
Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View
ARISE: Graph Anomaly Detection on Attributed Networks via Substructure Awareness
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.