221 citations · 587 across the 12 of their papers we have counts for
13 papers
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…
FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
Yunfeng Zhao, Yixin Liu, Shiyuan Li +3
Graph Anomaly Detection (GAD) aims to identify nodes that deviate from the majority within a graph, playing a crucial role in applications such as social networks and e-commerce. D…
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…
Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values
Yu Zheng, Huan Yee Koh, Ming Jin +6
The detection of anomalies in multivariate time series data is crucial for various practical applications, including smart power grids, traffic flow forecasting, and industrial pro…
Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook
Ming Jin, Yaxuan Kong, Yuxuan Liang +13
Temporal data, including time series and spatio-temporal data, are pervasive in real-world applications. Generated in massive volumes by physical and virtual sensors, they record d…
Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detection
Yu Zheng, Huan Yee Koh, Ming Jin +5
Multivariate time-series anomaly detection is critically important in many applications, including retail, transportation, power grid, and water treatment plants. Existing approach…
Finding the Missing-half: Graph Complementary Learning for Homophily-prone and Heterophily-prone Graphs
Yizhen Zheng, He Zhang, Vincent CS Lee +3
Real-world graphs generally have only one kind of tendency in their connections. These connections are either homophily-prone or heterophily-prone. While graphs with homophily-pron…
Unifying Graph Contrastive Learning with Flexible Contextual Scopes
Yizhen Zheng, Yu Zheng, Xiaofei Zhou +3
Graph contrastive learning (GCL) has recently emerged as an effective learning paradigm to alleviate the reliance on labelling information for graph representation learning. The co…
Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discrimination
Yizhen Zheng, Shirui Pan, Vincent Cs Lee +2
Graph contrastive learning (GCL) alleviates the heavy reliance on label information for graph representation learning (GRL) via self-supervised learning schemes. The core idea is t…
Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
Ming Jin, Yu Zheng, Yuan-Fang Li +3
Multivariate time series forecasting has long received significant attention in real-world applications, such as energy consumption and traffic prediction. While recent methods dem…
From Unsupervised to Few-shot Graph Anomaly Detection: A Multi-scale Contrastive Learning Approach
Yu Zheng, Ming Jin, Yixin Liu +3
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 detectio…
Towards Unsupervised Deep Graph Structure Learning
Yixin Liu, Yu Zheng, Daokun Zhang +3
In recent years, graph neural networks (GNNs) have emerged as a successful tool in a variety of graph-related applications. However, the performance of GNNs can be deteriorated whe…
Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
Yu Zheng, Ming Jin, Yixin Liu +3
Anomaly detection from graph data has drawn much attention due to its practical significance in many critical applications including cybersecurity, finance, and social networks. Ex…