# AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection

arXiv: https://arxiv.org/abs/2601.21171 · HTML: https://mlsanity.com/paper/2601.21171/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 29 Jan 2026.

## Builds on (most cited first, 18 of 18)

- [Graph Contrastive Learning with Augmentations](https://mlsanity.com/paper/2010.13902/) (2020)
- [Deep Graph Contrastive Representation Learning](https://mlsanity.com/paper/2006.04131/) (2020)
- [SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentation](https://mlsanity.com/paper/2202.03104/) (2022)
- [Data Augmentation for Deep Graph Learning: A Survey](https://mlsanity.com/paper/2202.08235/) (2022)
- [AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks](https://mlsanity.com/paper/2002.03665/) (2020)
- [GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection](https://mlsanity.com/paper/2306.12251/) (2023)
- [Graph Anomaly Detection via Multi-Scale Contrastive Learning Networks with Augmented View](https://mlsanity.com/paper/2212.00535/) (2022)
- [GAD-NR: Graph Anomaly Detection via Neighborhood Reconstruction](https://mlsanity.com/paper/2306.01951/) (2023)
- [Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection](https://mlsanity.com/paper/2306.00006/) (2023)
- [Scalable Anomaly Ranking of Attributed Neighborhoods](https://mlsanity.com/paper/1601.06711/) (2016)
- [Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2205.04816/) (2022)
- [ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection](https://mlsanity.com/paper/2312.14535/) (2023)
- [Generating Counterfactual Hard Negative Samples for Graph Contrastive Learning](https://mlsanity.com/paper/2207.00148/) (2022)
- [Higher-order Structure Based Anomaly Detection on Attributed Networks](https://mlsanity.com/paper/2406.04690/) (2024)
- [SmoothGNN: Smoothing-aware GNN for Unsupervised Node Anomaly Detection](https://mlsanity.com/paper/2405.17525/) (2024)
- [RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation](https://mlsanity.com/paper/2407.20684/) (2024)
- [Cluster Aware Graph Anomaly Detection](https://mlsanity.com/paper/2409.09770/) (2024)
- [Revisiting Graph Contrastive Learning on Anomaly Detection: A Structural Imbalance Perspective](https://mlsanity.com/paper/2507.14677/) (2025)

## Built on by (most cited first, 1 of 1)

- [Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory](https://mlsanity.com/paper/2604.07863/) (2026)

## Abstract (arXiv)

Graph anomaly detection aims to identify abnormal patterns in networks, but faces significant challenges from label scarcity and extreme class imbalance. While graph contrastive learning offers a promising unsupervised solution, existing methods suffer from two critical limitations: random augmentations break semantic consistency in positive pairs, while naive negative sampling produces trivial, uninformative contrasts. We propose AC2L-GAD, an Active Counterfactual Contrastive Learning framework that addresses both limitations through principled counterfactual reasoning. By combining information-theoretic active selection with counterfactual generation, our approach identifies structurally complex nodes and generates anomaly-preserving positive augmentations alongside normal negative counterparts that provide hard contrasts, while restricting expensive counterfactual generation to a strategically selected subset. This design reduces computational overhead by approximately 65% compared to full-graph counterfactual generation while maintaining detection quality. Experiments on nine benchmark datasets, including real-world financial transaction graphs from GADBench, show that AC2L-GAD achieves competitive or superior performance compared to state-of-the-art baselines, with notable gains in datasets where anomalies exhibit complex attribute-structure interactions.