{"type":"ScholarlyArticle","title":"Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Prompts","authors":[{"name":"Chaoxi Niu","slug":"chaoxi-niu","given":"Chaoxi","family":"Niu","affiliation":""},{"name":"Hezhe Qiao","slug":"hezhe-qiao","given":"Hezhe","family":"Qiao","affiliation":""},{"name":"Changlu Chen","slug":"changlu-chen","given":"Changlu","family":"Chen","affiliation":""},{"name":"Ling Chen","slug":"ling-chen","given":"Ling","family":"Chen","affiliation":""},{"name":"Guansong Pang","slug":"guansong-pang","given":"Guansong","family":"Pang","affiliation":""}],"abstract":"Graph anomaly detection (GAD), which aims to identify nodes in a graph that significantly deviate from normal patterns, plays a crucial role in broad application domains. However, existing GAD methods are one-model-for-one-dataset approaches, i.e., training a separate model for each graph dataset. This largely limits their applicability in real-world scenarios. To overcome this limitation, we propose a novel zero-shot generalist GAD approach UNPrompt that trains a one-for-all detection model, requiring the training of one GAD model on a single graph dataset and then effectively generalizing to detect anomalies in other graph datasets without any retraining or fine-tuning. The key insight in UNPrompt is that i) the predictability of latent node attributes can serve as a generalized anomaly measure and ii) generalized normal and abnormal graph patterns can be learned via latent node attribute prediction in a properly normalized node attribute space. UNPrompt achieves a generalist mode for GAD through two main modules: one module aligns the dimensionality and semantics of node attributes across different graphs via coordinate-wise normalization, while another module learns generalized neighborhood prompts that support the use of latent node attribute predictability as an anomaly score across different datasets. Extensive experiments on real-world GAD datasets show that UNPrompt significantly outperforms diverse competing methods under the generalist GAD setting, and it also has strong superiority under the one-model-for-one-dataset setting. Code is available at https://github.com/mala-lab/UNPrompt.","doi":"10.24963/ijcai.2025/359","url":"https://ijcai.org/proceedings/2025/359","pdf":"https://ijcai.org/proceedings/2025/0359.pdf","markdown":"https://ijcai.org/proceedings/2025/359.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/359","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Data Mining","track":"Main Track","number":359,"pages":{"first":3226,"last":3234},"keywords":["Data Mining: DM: Mining graphs","Data Mining: DM: Anomaly/outlier detection"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}