activity
20242026
most citedNoise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation

7 citations · 9 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

6 papers · 1 filter

cs.LG2026

Towards Anomaly Detection on Relational Data

Shiyuan Li, Yunfeng Zhao, Yue Tan +3

Relational databases are widely used for managing structured data in real-world systems. Detecting anomalies from such relational data is crucial for identifying fraud, risks, and…

cs.LG2026

Towards One-for-All Anomaly Detection for Tabular Data

Shiyuan Li, Yixin Liu, Yu Zheng +3

Tabular anomaly detection (TAD) aims to identify samples that deviate from the majority in tabular data and is critical in many real-world applications. However, existing methods f…

cs.LG2025

Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach

Qingfeng Chen, Shiyuan Li, Yixin Liu +3

Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertai…

cs.LG2025

GenIAS: Generator for Instantiating Anomalies in time Series

Zahra Zamanzadeh Darban, Qizhou Wang, Geoffrey I. Webb +3

Synthetic anomaly injection is a recent and promising approach for time series anomaly detection (TSAD), but existing methods rely on ad hoc, hand-crafted strategies applied to raw…

cs.LG20247 cited

Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation

Shiyuan Li, Yixin Liu, Qingfeng Chen +2

Unsupervised graph representation learning (UGRL) based on graph neural networks (GNNs), has received increasing attention owing to its efficacy in handling graph-structured data.…

cs.LG2024

ARC: A Generalist Graph Anomaly Detector with In-Context Learning

Yixin Liu, Shiyuan Li, Yu Zheng +3

Graph anomaly detection (GAD), which aims to identify abnormal nodes that differ from the majority within a graph, has garnered significant attention. However, current GAD methods…