---
title: "Unsupervised Graph-Level Anomaly Detection via Multi-granular Graph Structure Learning"
authors:
  - "Ge Zhang"
  - "Huimei Li"
  - "Guohao Sun"
  - "Xiu Fang"
  - "Xixun Lin"
  - "Xiaobao Wang"
  - "Pengfei Jiao"
  - "Liang Yang"
doi: "10.24963/ijcai.2026/355"
url: "https://ijcai.org/proceedings/2026/355"
pdf: "https://ijcai.org/proceedings/2026/0355.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3196-3204"
track: "Main Track"
keywords:
  - "Data Mining: Anomaly/outlier detection"
  - "Data Mining: Mining graphs"
---

# Unsupervised Graph-Level Anomaly Detection via Multi-granular Graph Structure Learning

Ge Zhang, Huimei Li, Guohao Sun, Xiu Fang, Xixun Lin, Xiaobao Wang, Pengfei Jiao, Liang Yang

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3196-3204. DOI: [10.24963/ijcai.2026/355](https://doi.org/10.24963/ijcai.2026/355)

## Abstract

Graph-level anomaly detection (GLAD) aims to identify graphs that deviate from the majority in a dataset of graphs. Existing methods typically adopt either a global aggregation perspective that summarizes nodes within a graph into a representation vector, or a subgraph-oriented perspective which regards certain local subgraphs as indicators of anomalous properties. However, both paradigms operate from a fixed perspective and may fail to identify anomalous graphs whose discriminative characteristics manifest at multiple levels of structure granularity, where each level features the coarsened graphs at a specific granularity. In this paper, we propose M-GLAD, an unsupervised GLAD method via multi-granular graph structure learning. M-GLAD is grounded in the Prototype-guided Multi-granular Information Bottleneck (PMIB) principle. PMIB aims to measure the mutual information between coarsened graphs at the specific level of structure granularity and the learnable granularity-specific prototypes that summarize normal patterns of graphs at each granularity. The multiple levels of structure granularity of graphs and prototypes are abstracted by a graph structure abstraction module. This formulation enables granularity-aware anomaly scoring that considers anomalous characteristics across different levels of structure granularity. Extensive experiments on eight real-world graph datasets demonstrate that M-GLAD achieves superior performance over competitive baselines.