activity
20182023
most citedDeep Learning for Time Series Anomaly Detection: A Survey

546 citations · 940 across the 9 of their papers we have counts for

collaborators

13 papers

cs.LG2023

Open-Set Graph Anomaly Detection via Normal Structure Regularisation

Qizhou Wang, Guansong Pang, Mahsa Salehi +2

This paper considers an important Graph Anomaly Detection (GAD) task, namely open-set GAD, which aims to train a detection model using a small number of normal and anomaly nodes (r…

cs.LG2023★ 142 cited

CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection

Zahra Zamanzadeh Darban, Geoffrey I. Webb, Shirui Pan +2

One main challenge in time series anomaly detection (TSAD) is the lack of labelled data in many real-life scenarios. Most of the existing anomaly detection methods focus on learnin…

cs.LG2023★ 233 cited

Improving Position Encoding of Transformers for Multivariate Time Series Classification

Navid Mohammadi Foumani, Chang Wei Tan, Geoffrey I. Webb +1

Transformers have demonstrated outstanding performance in many applications of deep learning. When applied to time series data, transformers require effective position encoding to…

cs.LG2023★ 4 cited

Proximity Forest 2.0: A new effective and scalable similarity-based classifier for time series

Matthieu Herrmann, Chang Wei Tan, Mahsa Salehi +1

Time series classification (TSC) is a challenging task due to the diversity of types of feature that may be relevant for different classification tasks, including trends, variance,…

cs.LG2023★ 10 cited

Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey

Navid Mohammadi Foumani, Lynn Miller, Chang Wei Tan +3

Time Series Classification and Extrinsic Regression are important and challenging machine learning tasks. Deep learning has revolutionized natural language processing and computer…

cs.LG2022★ 1 cited

Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignment

Qizhou Wang, Guansong Pang, Mahsa Salehi +2

Cross-domain graph anomaly detection (CD-GAD) describes the problem of detecting anomalous nodes in an unlabelled target graph using auxiliary, related source graphs with labelled…