Tony Q. S. Quek

Deep fusion of heterogeneous sensor data

2017

Heterogeneous sensor data fusion is a challenging field that has gathered significant interest in recent years. In this paper, we propose a neural network-based multimodal data fusion framework named deep multimodal encoder (DME). Through our …

Training Classifiers that are Universally Robust to All Label Noise Levels

2021

For classification tasks, deep neural networks are prone to overfitting in the presence of label noise. Although existing methods are able to alleviate this problem at low noise levels, they encounter significant performance reduction at …

DPP-based Client Selection for Federated Learning with Non-IID Data

2023 · arXiv (Cornell University)

This paper proposes a client selection (CS) method to tackle the communication bottleneck of federated learning (FL) while concurrently coping with FL's data heterogeneity issue. Specifically, we first analyze the effect of CS in FL …

Physical-layer Adversarial Robustness for Deep Learning-based Semantic Communications

2023 · arXiv (Cornell University)

End-to-end semantic communications (ESC) rely on deep neural networks (DNN) to boost communication efficiency by only transmitting the semantics of data, showing great potential for high-demand mobile applications. We argue that central to the success …

Privacy-Preserving Federated Primal—Dual Learning for Nonconvex and Nonsmooth Problems With Model Sparsification

2024 · IEEE Internet of Things Journal

Federated learning (FL) has been recognized as a rapidly growing research area, where the model is trained over massively distributed clients under the orchestration of a parameter server (PS) without sharing clients’ data. This paper …

Hierarchical Federated Edge Learning With Adaptive Clustering in Internet of Things

2024 · IEEE Internet of Things Journal

The expansion of the Internet of Things (IoT) has led to a significant surge in data flow over edge networks, posing substantial challenges to data mining and management. While federated edge learning (FEEL) effectively accomplishes …

Intelligent Covert Communication: Recent Advances and Future Research Trends

2024 · Engineering

With the future substantial increase in coverage and network heterogeneity, emerging networks will encounter unprecedented security threats. Covert communication is considered a potential enhanced security and privacy solution for safeguarding future wireless networks, as it …