116 citations · 207 across the 10 of their papers we have counts for
10 papers
ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths
Ruslan Khalitov, Tong Yu, Lei Cheng +1
Sequential data naturally have different lengths in many domains, with some very long sequences. As an important modeling tool, neural attention should capture long-range interacti…
Rethinking Bayesian Learning for Data Analysis: The Art of Prior and Inference in Sparsity-Aware Modeling
Lei Cheng, Feng Yin, Sergios Theodoridis +2
Sparse modeling for signal processing and machine learning has been at the focus of scientific research for over two decades. Among others, supervised sparsity-aware learning compr…
Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention
Tong Yu, Ruslan Khalitov, Lei Cheng +1
Self-Attention is a widely used building block in neural modeling to mix long-range data elements. Most self-attention neural networks employ pairwise dot-products to specify the a…
Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search
Chunhui Zhang, Xiaoming Yuan, Qianyun Zhang +3
Neural networks often encounter various stringent resource constraints while deploying on edge devices. To tackle these problems with less human efforts, automated machine learning…
Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks
Lei Cheng, Ruslan Khalitov, Tong Yu +1
Classification of long sequential data is an important Machine Learning task and appears in many application scenarios. Recurrent Neural Networks, Transformers, and Convolutional N…
Training Time Minimization for Federated Edge Learning with Optimized Gradient Quantization and Bandwidth Allocation
Peixi Liu, Jiamo Jiang, Guangxu Zhu +5
Training a machine learning model with federated edge learning (FEEL) is typically time-consuming due to the constrained computation power of edge devices and limited wireless reso…
RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation
Chenglin Li, Mingjun Zhao, Huanming Zhang +5
Cross-domain recommendation can help alleviate the data sparsity issue in traditional sequential recommender systems. In this paper, we propose the RecGURU algorithm framework to g…
Sparse Factorization of Large Square Matrices
Ruslan Khalitov, Tong Yu, Lei Cheng +1
Square matrices appear in many machine learning problems and models. Optimization over a large square matrix is expensive in memory and in time. Therefore an economic approximation…
A Bayesian Tensor Approach to Enable RIS for 6G Massive Unsourced Random Access
Xiaodan Shao, Lei Cheng, Xiaoming Chen +2
This paper investigates the problem of joint massive devices separation and channel estimation for a reconfigurable intelligent surface (RIS)-aided unsourced random access (URA) sc…
Similarity Embedding Networks for Robust Human Activity Recognition
Chenglin Li, Carrie Lu Tong, Di Niu +5
Deep learning models for human activity recognition (HAR) based on sensor data have been heavily studied recently. However, the generalization ability of deep models on complex rea…