32 citations · 89 across the 28 of their papers we have counts for
6 papers · 1 filter
MESEN: Exploit Multimodal Data to Design Unimodal Human Activity Recognition with Few Labels
Lilin Xu, Chaojie Gu, Rui Tan +2
Human activity recognition (HAR) will be an essential function of various emerging applications. However, HAR typically encounters challenges related to modality limitations and la…
Label-Free Multivariate Time Series Anomaly Detection
Qihang Zhou, Shibo He, Haoyu Liu +2
Anomaly detection in multivariate time series (MTS) has been widely studied in one-class classification (OCC) setting. The training samples in OCC are assumed to be normal, which i…
Confidant: Customizing Transformer-based LLMs via Collaborative Edge Training
Yuhao Chen, Yuxuan Yan, Qianqian Yang +3
Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks. Nonetheless, it is challenging to…
AccEPT: An Acceleration Scheme for Speeding Up Edge Pipeline-parallel Training
Yuhao Chen, Yuxuan Yan, Qianqian Yang +4
It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applica…
FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Framework for Heterogeneous Edge Devices
Yuhao Chen, Qianqian Yang, Shibo He +2
With the increased penetration and proliferation of Internet of Things (IoT) devices, there is a growing trend towards distributing the power of deep learning (DL) across edge devi…
Fairness-aware Outlier Ensemble
Haoyu Liu, Fenglong Ma, Shibo He +2
Outlier ensemble methods have shown outstanding performance on the discovery of instances that are significantly different from the majority of the data. However, without the aware…