activity
20182024
most citedTime-Series Representation Learning via Temporal and Contextual Contrasting

36 citations · 57 across the 10 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2024

Self-evolving Autoencoder Embedded Q-Network

J. Senthilnath, Bangjian Zhou, Zhen Wei Ng +7

In the realm of sequential decision-making tasks, the exploration capability of a reinforcement learning (RL) agent is paramount for achieving high rewards through interactions wit…

cs.LG2024

Evolving Restricted Boltzmann Machine-Kohonen Network for Online Clustering

J. Senthilnath, Adithya Bhattiprolu, Ankur Singh +4

A novel online clustering algorithm is presented where an Evolving Restricted Boltzmann Machine (ERBM) is embedded with a Kohonen Network called ERBM-KNet. The proposed ERBM-KNet e…

cs.LG2023

Fully-Connected Spatial-Temporal Graph for Multivariate Time-Series Data

Yucheng Wang, Yuecong Xu, Jianfei Yang +4

Multivariate Time-Series (MTS) data is crucial in various application fields. With its sequential and multi-source (multiple sensors) properties, MTS data inherently exhibits Spati…

cs.LG2023

Graph-Aware Contrasting for Multivariate Time-Series Classification

Yucheng Wang, Yuecong Xu, Jianfei Yang +4

Contrastive learning, as a self-supervised learning paradigm, becomes popular for Multivariate Time-Series (MTS) classification. It ensures the consistency across different views o…

cs.LG2023

Distilling Universal and Joint Knowledge for Cross-Domain Model Compression on Time Series Data

Qing Xu, Min Wu, Xiaoli Li +2

For many real-world time series tasks, the computational complexity of prevalent deep leaning models often hinders the deployment on resource-limited environments (e.g., smartphone…

cs.LG202136 cited

Time-Series Representation Learning via Temporal and Contextual Contrasting

Emadeldeen Eldele, Mohamed Ragab, Zhenghua Chen +4

Learning decent representations from unlabeled time-series data with temporal dynamics is a very challenging task. In this paper, we propose an unsupervised Time-Series representat…