# Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphs

arXiv: https://arxiv.org/abs/2501.15035 · HTML: https://mlsanity.com/paper/2501.15035/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 25 Jan 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Inductive Representation Learning on Temporal Graphs](https://mlsanity.com/paper/2002.07962/) (2020)
- [Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks](https://mlsanity.com/paper/1908.01207/) (2019)
- [Structure-Aware Transformer for Graph Representation Learning](https://mlsanity.com/paper/2202.03036/) (2022)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [A Semi-supervised Graph Attentive Network for Financial Fraud Detection](https://mlsanity.com/paper/2003.01171/) (2020)
- [Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection](https://mlsanity.com/paper/2108.09896/) (2021)
- [Few-shot Network Anomaly Detection via Cross-network Meta-learning](https://mlsanity.com/paper/2102.11165/) (2021)
- [Anomaly Detection in Dynamic Graphs via Transformer](https://mlsanity.com/paper/2106.09876/) (2021)
- [Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs](https://mlsanity.com/paper/2005.07427/) (2020)
- [Rethinking Assumptions in Deep Anomaly Detection](https://mlsanity.com/paper/2006.00339/) (2020)
- [Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2205.04816/) (2022)
- [SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs](https://mlsanity.com/paper/2305.13573/) (2023)
- [PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection](https://mlsanity.com/paper/2310.11676/) (2023)
- [Semi-supervised Anomaly Detection on Attributed Graphs](https://mlsanity.com/paper/2002.12011/) (2020)
- [AntiBenford Subgraphs: Unsupervised Anomaly Detection in Financial Networks](https://mlsanity.com/paper/2205.13426/) (2022)
- [Towards Cross-domain Few-shot Graph Anomaly Detection](https://mlsanity.com/paper/2410.08629/) (2024)

## Built on by (most cited first, 2 of 2)

- [Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories](https://mlsanity.com/paper/2510.12686/) (2025)
- [Prospective Multi-Graph Cohesion for Multivariate Time Series Anomaly Detection](https://mlsanity.com/paper/2509.17235/) (2025)

## Abstract (arXiv)

Semi-supervised graph anomaly detection (GAD) has recently received increasing attention, which aims to distinguish anomalous patterns from graphs under the guidance of a moderate amount of labeled data and a large volume of unlabeled data. Although these proposed semi-supervised GAD methods have achieved great success, their superior performance will be seriously degraded when the provided labels are extremely limited due to some unpredictable factors. Besides, the existing methods primarily focus on anomaly detection in static graphs, and little effort was paid to consider the continuous evolution characteristic of graphs over time (dynamic graphs). To address these challenges, we propose a novel GAD framework (EL2-DGAD) to tackle anomaly detection problem in dynamic graphs with extremely limited labels. Specifically, a transformer-based graph encoder model is designed to more effectively preserve evolving graph structures beyond the local neighborhood. Then, we incorporate an ego-context hypersphere classification loss to classify temporal interactions according to their structure and temporal neighborhoods while ensuring the normal samples are mapped compactly against anomalous data. Finally, the above loss is further augmented with an ego-context contrasting module which utilizes unlabeled data to enhance model generalization. Extensive experiments on four datasets and three label rates demonstrate the effectiveness of the proposed method in comparison to the existing GAD methods.