AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Towards Generalist Graph-Level Anomaly Detection

Junjun Pan, Yixin Liu, Yu Zheng, Fuyi Li, Alan Wee-Chung Liew, Shirui Pan

NeurIPS 2026 · Graph learning › Graph self-supervised learning · approach: Graph anomaly detection · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a generalist approach to graph-level anomaly detection that aims to work across datasets and domains rather than training a separate model per dataset.

Problem

Graph-level anomaly detection (GLAD) typically follows a dataset-specific paradigm, requiring substantial in-domain data and training cost when applied to new application scenarios.

Approach

Shifts GLAD from a dataset-specific paradigm toward a generalist setting that transfers to new scenarios without per-dataset training; the abstract is truncated so the specific mechanism is not stated.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add node-level pseudo-anomaly loss during pre-training (ablation)GenGLAD · IMDB-BINARYAUROC: 58.03 -> 74.11Improved
add L1 sparsity regularization on the subgraph mask (ablation)GenGLAD · IMDB-BINARYAUROC: 60.06 -> 74.11Improved
add class-level discrepancy score (ablation)GenGLAD · DHFRAUROC: 45.63 -> 74.96Improved
add domain discrepancy score (ablation)GenGLAD · IMDB-BINARYAUROC: 51.65 -> 74.11Improved
add prior discrepancy score (ablation)GenGLAD · IMDB-BINARYAUROC: 71.15 -> 74.11Improved
add instance-level discrepancy score (ablation)GenGLAD · PROTEINSAUROC: 73.75 -> 73.63No clear effect
use learned linear scoring module instead of mean/max/min aggregation (ablation)GenGLAD · DHFRAUROC: 28.92 -> 74.96Improved
add cross-domain pre-training before few-shot fine-tuning for conventional GLAD baselinesGLAD baselines · 10 test datasetsAUROCNo clear effect
increase number of pre-training datasets (ablation)GenGLAD · test datasetsAUROCImproved
increase number of few-shot normal graphs for adaptation (ablation)GenGLAD · social networksAUROCImproved
increase number of retrieved memory tokens K beyond a threshold (ablation)GenGLAD · science graphs and social networksAUROCHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy