Alert button
Picture for Guangyu Zhu

Guangyu Zhu

Alert button

Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks

Apr 07, 2023
Zheng Lin, Guangyu Zhu, Yiqin Deng, Xianhao Chen, Yue Gao, Kaibin Huang, Yuguang Fang

Figure 1 for Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks
Figure 2 for Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks
Figure 3 for Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks
Figure 4 for Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks

The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices. To overcome this challenge, in this paper, we advocate the integration of edge computing paradigm and parallel split learning (PSL), allowing multiple client devices to offload substantial training workloads to an edge server via layer-wise model split. By observing that existing PSL schemes incur excessive training latency and large volume of data transmissions, we propose an innovative PSL framework, namely, efficient parallel split learning (EPSL), to accelerate model training. To be specific, EPSL parallelizes client-side model training and reduces the dimension of local gradients for back propagation (BP) via last-layer gradient aggregation, leading to a significant reduction in server-side training and communication latency. Moreover, by considering the heterogeneous channel conditions and computing capabilities at client devices, we jointly optimize subchannel allocation, power control, and cut layer selection to minimize the per-round latency. Simulation results show that the proposed EPSL framework significantly decreases the training latency needed to achieve a target accuracy compared with the state-of-the-art benchmarks, and the tailored resource management and layer split strategy can considerably reduce latency than the counterpart without optimization.

* 15 pages, 13 figures 
Viaarxiv icon

Cost-aware Generalized $α$-investing for Multiple Hypothesis Testing

Oct 31, 2022
Thomas Cook, Harsh Vardhan Dubey, Ji Ah Lee, Guangyu Zhu, Tingting Zhao, Patrick Flaherty

Figure 1 for Cost-aware Generalized $α$-investing for Multiple Hypothesis Testing
Figure 2 for Cost-aware Generalized $α$-investing for Multiple Hypothesis Testing
Figure 3 for Cost-aware Generalized $α$-investing for Multiple Hypothesis Testing
Figure 4 for Cost-aware Generalized $α$-investing for Multiple Hypothesis Testing

We consider the problem of sequential multiple hypothesis testing with nontrivial data collection cost. This problem appears, for example, when conducting biological experiments to identify differentially expressed genes in a disease process. This work builds on the generalized $\alpha$-investing framework that enables control of the false discovery rate in a sequential testing setting. We make a theoretical analysis of the long term asymptotic behavior of $\alpha$-wealth which motivates a consideration of sample size in the $\alpha$-investing decision rule. Using the game theoretic principle of indifference, we construct a decision rule that optimizes the expected return (ERO) of $\alpha$-wealth and provides an optimal sample size for the test. We show empirical results that a cost-aware ERO decision rule correctly rejects more false null hypotheses than other methods. We extend cost-aware ERO investing to finite-horizon testing which enables the decision rule to hedge against the risk of unproductive tests. Finally, empirical tests on a real data set from a biological experiment show that cost-aware ERO produces actionable decisions as to which tests to conduct and if so at what sample size.

* 21 pages, 4 figures, 7 tables 
Viaarxiv icon

Actions at the Edge: Jointly Optimizing the Resources in Multi-access Edge Computing

Apr 18, 2022
Yiqin Deng, Xianhao Chen, Guangyu Zhu, Yuguang Fang, Zhigang Chen, Xiaoheng Deng

Figure 1 for Actions at the Edge: Jointly Optimizing the Resources in Multi-access Edge Computing
Figure 2 for Actions at the Edge: Jointly Optimizing the Resources in Multi-access Edge Computing

Multi-access edge computing (MEC) is an emerging paradigm that pushes resources for sensing, communications, computing, storage and intelligence (SCCSI) to the premises closer to the end users, i.e., the edge, so that they could leverage the nearby rich resources to improve their quality of experience (QoE). Due to the growing emerging applications targeting at intelligentizing life-sustaining cyber-physical systems, this paradigm has become a hot research topic, particularly when MEC is utilized to provide edge intelligence and real-time processing and control. This article is to elaborate the research issues along this line, including basic concepts and performance metrics, killer applications, architectural design, modeling approaches and solutions, and future research directions. It is hoped that this article provides a quick introduction to this fruitful research area particularly for beginning researchers.

* 7 pages, 2 figures, accepted by IEEE Wireless Communications 
Viaarxiv icon

Deep-gKnock: nonlinear group-feature selection with deep neural network

May 27, 2019
Guangyu Zhu, Tingting Zhao

Figure 1 for Deep-gKnock: nonlinear group-feature selection with deep neural network
Figure 2 for Deep-gKnock: nonlinear group-feature selection with deep neural network
Figure 3 for Deep-gKnock: nonlinear group-feature selection with deep neural network
Figure 4 for Deep-gKnock: nonlinear group-feature selection with deep neural network

Feature selection is central to contemporary high-dimensional data analysis. Grouping structure among features arises naturally in various scientific problems. Many methods have been proposed to incorporate the grouping structure information into feature selection. However, these methods are normally restricted to a linear regression setting. To relax the linear constraint, we combine the deep neural networks (DNNs) with the recent Knockoffs technique, which has been successful in an individual feature selection context. We propose Deep-gKnock (Deep group-feature selection using Knockoffs) as a methodology for model interpretation and dimension reduction. Deep-gKnock performs model-free group-feature selection by controlling group-wise False Discovery Rate (gFDR). Our method improves the interpretability and reproducibility of DNNs. Experimental results on both synthetic and real data demonstrate that our method achieves superior power and accurate gFDR control compared with state-of-the-art methods.

Viaarxiv icon