Graph Anomaly Detection

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 50 papers with code (87 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Energy Transformer
  14 Feb 2023 4 repositories listed Syntology ran 8 of 13 samples · 5 unverified · 3 pointer-only (licence)
  Our work combines aspects of three promising paradigms in machine learning, namely, attention mechanism, energy-based models, and associative memory.
• Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection
  22 Apr 2025 3 repositories listed
  Specifically, fraudsters disguise themselves by mimicking the behavioral data collected by platforms, ensuring that their key characteristics are consistent with those of benign users to a high degree, which we call…
• One-Class Graph Neural Networks for Anomaly Detection in Attributed Networks
  22 Feb 2020 3 repositories listed
  Since traditional anomaly detection methods are stable, robust and easy to use, it is vitally important to generalize them to graph data.
• Label-based Graph Augmentation with Metapath for Graph Anomaly Detection
  21 Aug 2023 2 repositories listed Syntology ran 3 of 4 samples · 1 unverified · 4 pointer-only (licence)
  To further efficiently exploit context information from metapath-based anomaly subgraph, we present a new framework, Metapath-based Graph Anomaly Detection (MGAD), incorporating GCN layers in both the dual-encoders and…
• Coupled-Space Attacks against Random-Walk-based Anomaly Detection
  26 Jul 2023 2 repositories listed
  In addition, we conduct transfer attack experiments in a black-box setting, which show that our feature attack significantly decreases the anomaly scores of target nodes.
• GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction
  2 Jun 2023 2 repositories listed
  Graph Anomaly Detection (GAD) is a technique used to identify abnormal nodes within graphs, finding applications in network security, fraud detection, social media spam detection, and various other domains.
• Chi-Square Wavelet Graph Neural Networks for Heterogeneous Graph Anomaly Detection
  25 May 2025 1 repository listed
  Graph Anomaly Detection (GAD) in heterogeneous networks presents unique challenges due to node and edge heterogeneity.
• Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening
  20 May 2025 1 repository listed
  Filtering-based graph neural networks (GNNs) constitute a distinct class of GNNs that employ graph filters to handle graph-structured data, achieving notable success in various graph-related tasks.
• Unsupervised Graph Anomaly Detection via Multi-Hypersphere Heterophilic Graph Learning
  15 Mar 2025 1 repository listed
  Specifically, we first devise a Heterophilic Graph Encoding (HGE) module to learn distinguishable representations for potential anomalies by purifying and augmenting their neighborhood in a fully unsupervised manner.
• AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection
  13 Feb 2025 1 repository listed
  To address this challenge, we propose AnomalyGFM, a GAD-oriented graph foundation model that supports zero-shot inference and few-shot prompt tuning for GAD in diverse graph datasets.
• Out-of-Distribution Detection on Graphs: A Survey
  12 Feb 2025 1 repository listed
  Graph machine learning has witnessed rapid growth, driving advancements across diverse domains.
• Towards Automated Self-Supervised Learning for Truly Unsupervised Graph Anomaly Detection
  24 Jan 2025 1 repository listed
  Self-supervised learning (SSL) is an emerging paradigm that exploits supervisory signals generated from the data itself, and many recent studies have leveraged SSL to conduct graph anomaly detection.
• UniGAD: Unifying Multi-level Graph Anomaly Detection
  10 Nov 2024 1 repository listed Syntology ran 3 of 13 samples · 10 unverified
  Existing methods generally focus on a single graph object type (node, edge, graph, etc.)
• High-Pass Graph Convolutional Network for Enhanced Anomaly Detection: A Novel Approach
  4 Nov 2024 1 repository listed
  To address this, the model segments the graph into isolated nodes and nodes within connected subgraphs.
• ANOMIX: A Simple yet Effective Hard Negative Generation via Mixing for Graph Anomaly Detection
  27 Oct 2024 1 repository listed
  ANOMIX is (a) A first mixing approach: firstly attempting graph mixing to generate hard negatives for GAD task and node- and subgraph-level contrasts to distinguish underlying anomalies.
• Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Prompts
  18 Oct 2024 1 repository listed Syntology ran 4 of 5 samples · 1 unverified
  Graph anomaly detection (GAD), which aims to identify nodes in a graph that significantly deviate from normal patterns, plays a crucial role in broad application domains.
• Revisiting Multi-Permutation Equivariance through the Lens of Irreducible Representations
  9 Oct 2024 1 repository listed Syntology ran 10 of 10 samples · 0 unverified · 10 pointer-only (licence)
  Using this methodology, we obtain an alternative derivation for existing models like DeepSets, 2-IGN graph equivariant networks, and Deep Weight Space (DWS) networks.
• DiffGAD: A Diffusion-based Unsupervised Graph Anomaly Detector
  9 Oct 2024 1 repository listed Syntology ran 4 of 6 samples · 2 unverified · 6 pointer-only (licence)
  Graph Anomaly Detection (GAD) is crucial for identifying abnormal entities within networks, garnering significant attention across various fields.
• Deep Graph Anomaly Detection: A Survey and New Perspectives
  16 Sep 2024 1 repository listed
  To this end, in this work we aim to present a comprehensive review of deep learning approaches for GAD.
• Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability
  1 Aug 2024 1 repository listed
  When new knowledge emerges, AnoT maps it onto a node in the rule graph and traverses the rule graph recursively to derive the anomaly score of the knowledge.
• Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detection
  2 Jul 2024 1 repository listed
  To tackle this issue, we propose CAGAD -- an unsupervised Counterfactual data Augmentation method for Graph Anomaly Detection -- which introduces a graph pointer neural network as the heterophilic node detector to…
• Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement
  3 Jun 2024 1 repository listed
  Graph anomaly detection (GAD) is increasingly crucial in various applications, ranging from financial fraud detection to fake news detection.
• ARC: A Generalist Graph Anomaly Detector with In-Context Learning
  27 May 2024 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Graph anomaly detection (GAD), which aims to identify abnormal nodes that differ from the majority within a graph, has garnered significant attention.
• Polynomial Selection in Spectral Graph Neural Networks: An Error-Sum of Function Slices Approach
  15 Apr 2024 1 repository listed
  Building on this, we then bridge the polynomial capability and spectral GNN efficacy by proving that the construction error of graph convolution layer is bounded by the sum of polynomial approximation errors on function…
• Three Revisits to Node-Level Graph Anomaly Detection: Outliers, Message Passing and Hyperbolic Neural Networks
  6 Mar 2024 1 repository listed
  Graph anomaly detection plays a vital role for identifying abnormal instances in complex networks.
• Towards Fair Graph Anomaly Detection: Problem, Benchmark Datasets, and Evaluation
  25 Feb 2024 1 repository listed
  The Fair Graph Anomaly Detection (FairGAD) problem aims to accurately detect anomalous nodes in an input graph while avoiding biased predictions against individuals from sensitive subgroups.
• Generative Semi-supervised Graph Anomaly Detection
  19 Feb 2024 1 repository listed Syntology ran 11 of 19 samples · 8 unverified · 14 pointer-only (licence)
  This work considers a practical semi-supervised graph anomaly detection (GAD) scenario, where part of the nodes in a graph are known to be normal, contrasting to the extensively explored unsupervised setting with a…
• Alleviating Structural Distribution Shift in Graph Anomaly Detection
  25 Jan 2024 1 repository listed Syntology ran 1 of 3 samples · 2 unverified · 3 pointer-only (licence)
  Graph anomaly detection (GAD) is a challenging binary classification problem due to its different structural distribution between anomalies and normal nodes -- abnormal nodes are a minority, therefore holding high…
• Multitask Active Learning for Graph Anomaly Detection
  24 Jan 2024 1 repository listed
  Firstly, by coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies.
• ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection
  22 Dec 2023 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns.

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.