# Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision

arXiv: https://arxiv.org/abs/2602.20019 · HTML: https://mlsanity.com/paper/2602.20019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 42 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 24 of 24)

- [Temporal Graph Networks for Deep Learning on Dynamic Graphs](https://mlsanity.com/paper/2006.10637/) (2020)
- [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)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [A Comprehensive Survey on Graph Anomaly Detection with Deep Learning](https://mlsanity.com/paper/2106.07178/) (2021)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks](https://mlsanity.com/paper/2101.05974/) (2021)
- [Towards Better Dynamic Graph Learning: New Architecture and Unified Library](https://mlsanity.com/paper/2303.13047/) (2023)
- [A Semi-supervised Graph Attentive Network for Financial Fraud Detection](https://mlsanity.com/paper/2003.01171/) (2020)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Do We Really Need Complicated Model Architectures For Temporal Networks?](https://mlsanity.com/paper/2302.11636/) (2023)
- [Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection](https://mlsanity.com/paper/2005.00625/) (2020)
- [TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning](https://mlsanity.com/paper/2105.07944/) (2021)
- [Anomaly Detection in Dynamic Graphs via Transformer](https://mlsanity.com/paper/2106.09876/) (2021)
- [Robust Optimization as Data Augmentation for Large-scale Graphs](https://mlsanity.com/paper/2010.09891/) (2020)
- [Structural Temporal Graph Neural Networks for Anomaly Detection in Dynamic Graphs](https://mlsanity.com/paper/2005.07427/) (2020)
- [Deep Graph Anomaly Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2409.09957/) (2024)
- [SAD: Semi-Supervised Anomaly Detection on Dynamic Graphs](https://mlsanity.com/paper/2305.13573/) (2023)
- [Deep Orthogonal Hypersphere Compression for Anomaly Detection](https://mlsanity.com/paper/2302.06430/) (2023)
- [A Generalizable Anomaly Detection Method in Dynamic Graphs](https://mlsanity.com/paper/2412.16447/) (2024)
- [Motif-aware temporal GCN for fraud detection in signed cryptocurrency trust networks](https://mlsanity.com/paper/2211.13123/) (2022)
- [Learning-Based Link Anomaly Detection in Continuous-Time Dynamic Graphs](https://mlsanity.com/paper/2405.18050/) (2024)
- [InFlow: Robust outlier detection utilizing Normalizing Flows](https://mlsanity.com/paper/2106.12894/) (2021)

## Abstract (arXiv)

Dynamic graph anomaly detection is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies. Existing methods are either unsupervised or semi-supervised: unsupervised methods avoid the need for labeled anomalies but often produce ambiguous boundary, whereas semi-supervised methods can overfit to the limited labeled anomalies and generalize poorly to unseen anomalies. To address this gap, we consider a largely underexplored problem: learning a discriminative boundary from normal/unlabeled data, while leveraging limited labeled anomalies when available without sacrificing generalization to unseen anomalies. In this paper, we propose an effective, generalizable, and model-agnostic framework with three main components: (i) residual representation encoding that capture deviations between current interactions and their historical context, providing anomaly-relevant signals; (ii) a restriction loss that constrain the normal representations within an interval bounded by two co-centered hyperspheres, ensuring consistent scales while keeping anomalies separable; (iii) a bi-boundary optimization strategy that learns a discriminative and robust boundary using the log-likelihood distribution modeled by a normalizing flow. Extensive experiments demonstrate the superiority of our framework across diverse evaluation settings.