Unifying unsupervised graph-level anomaly detection and out-of-distribution detection: A benchmark

Y Wang, Y Liu, X Shen, C Li, K Ding, R Miao… - arxiv preprint arxiv …, 2024 - arxiv.org
To build safe and reliable graph machine learning systems, unsupervised graph-level
anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection …

GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation

D Wang, R Qiu, G Bai, Z Huang - arxiv preprint arxiv:2502.05780, 2025 - arxiv.org
Despite graph neural networks'(GNNs) great success in modelling graph-structured data,
out-of-distribution (OOD) test instances still pose a great challenge for current GNNs. One of …

From unsupervised to few-shot graph anomaly detection: A multi-scale contrastive learning approach

Y Zheng, M **, Y Liu, L Chi, KT Phan… - arxiv preprint arxiv …, 2022 - arxiv.org
Anomaly detection from graph data is an important data mining task in many applications
such as social networks, finance, and e-commerce. Existing efforts in graph anomaly …

Rethinking independent cross-entropy loss for graph-structured data

R Miao, K Zhou, Y Wang, N Liu, Y Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Graph neural networks (GNNs) have exhibited prominent performance in learning graph-
structured data. Considering node classification task, based on the iid assumption among …

Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion

H Gu, K Zhou, Y Wang, R Wang, X Wang - arxiv preprint arxiv:2409.17928, 2024 - arxiv.org
During pre-training, the Text-to-Image (T2I) diffusion models encode factual knowledge into
their parameters. These parameterized facts enable realistic image generation, but they may …

Out-of-Distribution Detection on Graphs: A Survey

T Cai, Y Jiang, Y Liu, M Li, C Huang, S Pan - arxiv preprint arxiv …, 2025 - arxiv.org
Graph machine learning has witnessed rapid growth, driving advancements across diverse
domains. However, the in-distribution assumption, where training and testing data share the …