# Multitask Active Learning for Graph Anomaly Detection

arXiv: https://arxiv.org/abs/2401.13210 · HTML: https://mlsanity.com/paper/2401.13210/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 24 Jan 2024.

## Builds on (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [Rethinking Graph Neural Networks for Anomaly Detection](https://mlsanity.com/paper/2205.15508/) (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)
- [Unsupervised Out-of-Distribution Detection by Maximum Classifier Discrepancy](https://mlsanity.com/paper/1908.04951/) (2019)
- [Uncertainty Aware Semi-Supervised Learning on Graph Data](https://mlsanity.com/paper/2010.12783/) (2020)
- [Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection](https://mlsanity.com/paper/2005.00625/) (2020)
- [Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification](https://mlsanity.com/paper/2110.14012/) (2021)
- [BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphs](https://mlsanity.com/paper/2206.10071/) (2022)
- [User Preference-aware Fake News Detection](https://mlsanity.com/paper/2104.12259/) (2021)
- [Toward Supervised Anomaly Detection](https://mlsanity.com/paper/1401.6424/) (2014)
- [Contrastive Out-of-Distribution Detection for Pretrained Transformers](https://mlsanity.com/paper/2104.08812/) (2021)
- [GeniePath: Graph Neural Networks with Adaptive Receptive Paths](https://mlsanity.com/paper/1802.00910/) (2018)
- [Few-shot Network Anomaly Detection via Cross-network Meta-learning](https://mlsanity.com/paper/2102.11165/) (2021)
- [A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning](https://mlsanity.com/paper/2101.01669/) (2021)
- [Active Learning for Graph Embedding](https://mlsanity.com/paper/1705.05085/) (2017)
- [ConsisRec: Enhancing GNN for Social Recommendation via Consistent Neighbor Aggregation](https://mlsanity.com/paper/2105.02254/) (2021)
- [Active Learning for Graph Neural Networks via Node Feature Propagation](https://mlsanity.com/paper/1910.07567/) (2019)
- [Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning](https://mlsanity.com/paper/2009.07415/) (2020)
- [Learning on Graphs with Out-of-Distribution Nodes](https://mlsanity.com/paper/2308.06714/) (2023)
- [DAGAD: Data Augmentation for Graph Anomaly Detection](https://mlsanity.com/paper/2210.09766/) (2022)
- [Effectiveness of Tree-based Ensembles for Anomaly Discovery: Insights, Batch and Streaming Active Learning](https://mlsanity.com/paper/1901.08930/) (2019)
- [Deep Anomaly Detection under Labeling Budget Constraints](https://mlsanity.com/paper/2302.07832/) (2023)
- [LSCALE: Latent Space Clustering-Based Active Learning for Node Classification](https://mlsanity.com/paper/2012.07065/) (2020)
- [Active Learning from Positive and Unlabeled Data](https://mlsanity.com/paper/1602.07495/) (2016)

## Built on by (most cited first, 7 of 7)

- [Deep Graph Anomaly Detection: A Survey and New Perspectives](https://mlsanity.com/paper/2409.09957/) (2024)
- [Uncertainty in Graph Neural Networks: A Survey](https://mlsanity.com/paper/2403.07185/) (2024)
- [LEGO-Learn: Label-Efficient Graph Open-Set Learning](https://mlsanity.com/paper/2410.16386/) (2024)
- [Few-Shot Graph Out-of-Distribution Detection with LLMs](https://mlsanity.com/paper/2503.22097/) (2025)
- [Enhancing Fairness in Unsupervised Graph Anomaly Detection through Disentanglement](https://mlsanity.com/paper/2406.00987/) (2024)
- [TGTOD: A Global Temporal Graph Transformer for Outlier Detection at Scale](https://mlsanity.com/paper/2412.00984/) (2024)
- [Metric Matters: A Formal Evaluation of Similarity Measures in Active Learning for Cyber Threat Intelligence](https://mlsanity.com/paper/2508.19019/) (2025)

## Abstract (arXiv)

In the web era, graph machine learning has been widely used on ubiquitous graph-structured data. As a pivotal component for bolstering web security and enhancing the robustness of graph-based applications, the significance of graph anomaly detection is continually increasing. While Graph Neural Networks (GNNs) have demonstrated efficacy in supervised and semi-supervised graph anomaly detection, their performance is contingent upon the availability of sufficient ground truth labels. The labor-intensive nature of identifying anomalies from complex graph structures poses a significant challenge in real-world applications. Despite that, the indirect supervision signals from other tasks (e.g., node classification) are relatively abundant. In this paper, we propose a novel MultItask acTIve Graph Anomaly deTEction framework, namely MITIGATE. Firstly, by coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies. Secondly, MITIGATE quantifies the informativeness of nodes by the confidence difference across tasks, allowing samples with conflicting predictions to provide informative yet not excessively challenging information for subsequent training. Finally, to enhance the likelihood of selecting representative nodes that are distant from known patterns, MITIGATE adopts a masked aggregation mechanism for distance measurement, considering both inherent features of nodes and current labeled status. Empirical studies on four datasets demonstrate that MITIGATE significantly outperforms the state-of-the-art methods for anomaly detection. Our code is publicly available at: https://github.com/AhaChang/MITIGATE.