# Interpretable Graph-Level Anomaly Detection via Contrast with Normal Prototypes

arXiv: https://arxiv.org/abs/2602.10708 · HTML: https://mlsanity.com/paper/2602.10708/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 11 Feb 2026.

## Builds on (most cited first, 16 of 16)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization](https://mlsanity.com/paper/1908.01000/) (2019)
- [graph2vec: Learning Distributed Representations of Graphs](https://mlsanity.com/paper/1707.05005/) (2017)
- [Discovering Invariant Rationales for Graph Neural Networks](https://mlsanity.com/paper/2201.12872/) (2022)
- [Wasserstein Weisfeiler-Lehman Graph Kernels](https://mlsanity.com/paper/1906.01277/) (2019)
- [Propagation Kernels](https://mlsanity.com/paper/1410.3314/) (2014)
- [Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation](https://mlsanity.com/paper/2112.10063/) (2021)
- [On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insights](https://mlsanity.com/paper/2012.12931/) (2020)
- [Raising the Bar in Graph-level Anomaly Detection](https://mlsanity.com/paper/2205.13845/) (2022)
- [Towards Self-Interpretable Graph-Level Anomaly Detection](https://mlsanity.com/paper/2310.16520/) (2023)
- [Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection](https://mlsanity.com/paper/2310.02861/) (2023)
- [Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy](https://mlsanity.com/paper/2410.20366/) (2024)
- [Nearest-Neighbour-Induced Isolation Similarity and its Impact on Density-Based Clustering](https://mlsanity.com/paper/1907.00378/) (2019)
- [Point-Set Kernel Clustering](https://mlsanity.com/paper/2002.05815/) (2020)

## Abstract (arXiv)

The task of graph-level anomaly detection (GLAD) is to identify anomalous graphs that deviate significantly from the majority of graphs in a dataset. While deep GLAD methods have shown promising performance, their black-box nature limits their reliability and deployment in real-world applications. Although some recent methods have made attempts to provide explanations for anomaly detection results, they either provide explanations without referencing normal graphs, or rely on abstract latent vectors as prototypes rather than concrete graphs from the dataset. To address these limitations, we propose Prototype-based Graph-Level Anomaly Detection (ProtoGLAD), an interpretable unsupervised framework that provides explanation for each detected anomaly by explicitly contrasting with its nearest normal prototype graph. It employs a point-set kernel to iteratively discover multiple normal prototype graphs and their associated clusters from the dataset, then identifying graphs distant from all discovered normal clusters as anomalies. Extensive experiments on multiple real-world datasets demonstrate that ProtoGLAD achieves competitive anomaly detection performance compared to state-of-the-art GLAD methods while providing better human-interpretable prototype-based explanations.