Graph-based time-series anomaly detection: A survey

TKK Ho, A Karami, N Armanfard - arxiv preprint arxiv:2302.00058, 2023 - arxiv.org
With the recent advances in technology, a wide range of systems continue to collect a large
amount of data over time and thus generate time series. Time-Series Anomaly Detection …

Universal time-series representation learning: A survey

P Trirat, Y Shin, J Kang, Y Nam, J Na, M Bae… - arxiv preprint arxiv …, 2024 - arxiv.org
Time-series data exists in every corner of real-world systems and services, ranging from
satellites in the sky to wearable devices on human bodies. Learning representations by …

[HTML][HTML] Learning transactions representations for information management in banks: Mastering local, global, and external knowledge

A Bazarova, M Kovaleva, I Kuleshov… - International Journal of …, 2025 - Elsevier
In today's world, banks use artificial intelligence to optimize diverse business processes,
aiming to improve customer experience. Most of the customer-related tasks can be …

ColaCare: Enhancing Electronic Health Record Modeling through Large Language Model-Driven Multi-Agent Collaboration

Z Wang, Y Zhu, H Zhao, X Zheng, T Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
We introduce ColaCare, a framework that enhances Electronic Health Record (EHR)
modeling through multi-agent collaboration driven by Large Language Models (LLMs). Our …

CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining

Z Hong, Z Li, S Zhong, W Lyu, H Wang, Y Ding… - Proceedings of the …, 2024 - dl.acm.org
The increasing availability of low-cost wearable devices and smartphones has significantly
advanced the field of sensor-based human activity recognition (HAR), attracting …

An Experimental Evaluation of Imputation Models for Spatial-Temporal Traffic Data

S Guo, T Wei, Y Huang, M Zhao, R Chen, Y Lin… - arxiv preprint arxiv …, 2024 - arxiv.org
Traffic data imputation is a critical preprocessing step in intelligent transportation systems,
enabling advanced transportation services. Despite significant advancements in this field …

DNA-T: Deformable Neighborhood Attention Transformer for Irregular Medical Time Series

J Huang, B Yang, K Yin, J Xu - IEEE Journal of Biomedical and …, 2024 - ieeexplore.ieee.org
The real-world Electronic Health Records (EHRs) present irregularities due to changes in
the patient's health status, resulting in various time intervals between observations and …

Unleashing the Power of Shared Label Structures for Human Activity Recognition

X Zhang, RR Chowdhury, J Zhang, D Hong… - Proceedings of the …, 2023 - dl.acm.org
Current human activity recognition (HAR) techniques regard activity labels as integer class
IDs without explicitly modeling the semantics of class labels. We observe that different …

TAMER: A Test-Time Adaptive MoE-Driven Framework for EHR Representation Learning

Y Zhu, X Zheng, A Allam, M Krauthammer - arxiv preprint arxiv …, 2025 - arxiv.org
We propose TAMER, a Test-time Adaptive MoE-driven framework for EHR Representation
learning. TAMER combines a Mixture-of-Experts (MoE) with Test-Time Adaptation (TTA) to …

SeqLink: A Robust Neural-ODE Architecture for Modelling Partially Observed Time Series

FM Abushaqra, H Xue, Y Ren… - Transactions on Machine …, 2024 - openreview.net
Ordinary Differential Equations (ODEs) based models have become popular as foundation
models for solving many time series problems. Combining neural ODEs with traditional RNN …