通过主动生成反事实样本，提升图异常检测的准确性与效率。
AC2L-GAD: Active Counterfactual Contrastive Learning for Graph Anomaly Detection
- 基于信息论选择复杂节点，仅对关键部分生成反事实增强
- 相比全图生成减少65%计算开销，保持检测性能
- 适合处理属性与结构耦合复杂的异常场景
图异常检测旨在识别网络中的异常模式，但面临标签稀缺和极端类别不平衡的挑战。现有图对比学习方法存在两大缺陷：随机增强破坏正样本语义一致性，简单负采样产生无意义对比。本文提出AC2L-GAD框架，通过信息论驱动的主动选择与反事实生成相结合，识别结构复杂的节点，并生成保留异常特性的正增强样本，同时构建提供困难对比的正常负样本。该设计将昂贵的反事实生成限制在精选子集，相较全图生成降低约65%计算开销，且维持检测质量。在九个基准数据集（包括GADBench的真实金融交易图）上的实验表明，该方法在性能上达到或优于当前最优基线，尤其在异常呈现复杂属性-结构交互的数据集中表现突出。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。