发表机构
School of Information and Communication Technology, Griffith University; School of Computer Science and Technology, Tongji University（格里菲斯大学信息与通信技术学院; 同济大学计算机科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对通用图异常检测的真实数据短缺问题，提出AG-FORGE合成异常图，开发TS-GGAD拓扑-语义协同模型结合课程学习，经14个真实数据集验证，其性能优于现有最先进方法。
AI 中文摘要
通用图异常检测（GAD）旨在构建一个基础模型，无需重新训练或微调即可检测任意未见图上的异常。基础模型训练需要充足数据，但通用GAD仍面临数据短缺问题，因为真实世界的异常图稀缺且收集标注成本高昂。为填补这一缺口，我们提出AG-FORGE，即用于自动合成异常图的异常图生成工具，探索合成数据驱动的通用GAD训练的可行性。实证研究发现，合成数据可达到与真实世界训练相当的性能，但受限于现有方法的有限容量，无法进一步突破性能边界。为在训练数据规模扩大时释放模型容量，我们开发TS-GGAD，即拓扑-语义协同通用GAD，其能捕获互补的拓扑和语义异常证据，同时结合针对大规模合成训练定制的课程学习策略。在14个真实世界数据集上的大量实验表明，基于AG-FORGE生成的数据训练的TS-GGAD，显著优于现有最先进方法。
英文摘要
Generalist graph anomaly detection (GAD) aims to build a foundation model that detects anomalies on arbitrary unseen graphs without retraining or fine-tuning. Sufficient data are essential for foundation model training, yet generalist GAD still faces a data shortage, as real-world anomalous graphs are scarce and costly to collect and annotate. To fill this gap, we propose AG-FORGE, an Anomalous Graph generation Forge for automatic synthesis of anomalous graphs, exploring the feasibility of synthetic data-driven training for generalist GAD. Empirically, we find that synthetic data can achieve performance comparable to real-world training, but fail to push the performance boundary further due to the limited capacity of existing methods. To further unlock model capacity as training data scale up, we develop TS-GGAD, a Topology-Semantic coordinated Generalist GAD that captures complementary topological and semantic anomaly evidence, together with a curriculum learning strategy tailored to large-scale synthetic training. Extensive experiments on 14 real-world datasets demonstrate that TS-GGAD, trained on data generated by AG-FORGE, significantly outperforms state-of-the-art methods.
Comments25 pages, 10 figures
