26 January 2024 in IEEE Transactions on Mobile Computing
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 edge 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 a 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 activations' gradients for backpropagation (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 edge 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.
7 May 2024 in IEEE Internet of Things Journal
Federated learning (FL) allows multiple parties (distributed devices) to train a machine learning model without sharing raw data. How to effectively and efficiently utilize the resources on devices and the central server is a highly interesting yet challenging problem. In this article, we propose an efficient split FL (ESFL) algorithm to take full advantage of the powerful computing capabilities at a central server under a split FL framework with heterogeneous end devices (EDs). By splitting the model into different submodels between the server and EDs, our approach jointly optimizes user-side workload and server-side computing resource allocation by considering users’ heterogeneity. We formulate the whole optimization problem as a mixed-integer nonlinear program, which is an NP-hard problem, and develop an iterative approach to obtain an approximate solution efficiently. Extensive simulations have been conducted to validate the significantly increased efficiency of our ESFL approach compared with standard FL, split learning, and splitfed learning.
27 April 2021 in IEEE Transactions on Network Science and Engineering
The risk of severe illness and mortality from COVID-19 significantly increases with age. As a result, age-stratified modeling for COVID-19 dynamics is the key to study how to reduce hospitalizations and mortality from COVID-19. By taking advantage of network theory, we develop an age-stratified epidemic model for COVID-19 in complex contact networks. Specifically, we present an extension of standard SEIR (susceptible-exposed-infectious-removed) compartmental model, called age-stratified SEAHIR (susceptible-exposed-asymptomatic-hospitalized-infectious-removed) model, to capture the spread of COVID-19 over multitype random networks with general degree distributions. We derive several key epidemiological metrics and then propose an age-stratified vaccination strategy to decrease the mortality and hospitalizations. Through extensive study, we discover that the outcome of vaccination prioritization depends on the reproduction number $R_0$ . Specifically, the elderly should be prioritized only when $R_0$ is relatively high. If ongoing intervention policies, such as universal masking, could suppress $R_0$ at a relatively low level, prioritizing the high-transmission age group (i.e., adults aged 20-39) is most effective to reduce both mortality and hospitalizations. These conclusions provide useful recommendations for age-based vaccination prioritization for COVID-19.
11 September 2022 in arXiv
In 5G and beyond, the newly emerging services, such as edge computing/intelligence services, may demand the provision of heterogeneous communications, computing, and storage (CCS) resources on and across network entities multihop apart. In such cases, traditional resource-oriented auction schemes, where buyers place bids on resources, may not be effective in providing end-to-end (E2E) quality-of-service (QoS) guarantees. To overcome these limitations, in this article, we coin the concept of E2E service auction where the auction commodities are E2E services rather than certain resource. Under this framework, buyers simply bid for services with E2E QoS requirements without having to know the inner working (which resources are behind). To guarantee E2E QoS for winning bids while ensuring essential economic properties, E2E service auction requires addressing the joint problem of network optimization and auction design with both economical and QoS constraints. To substantiate the mechanism design, we illustrate how to devise E2E service auctions for edge computing systems under various scenarios. We also identify the research opportunities on E2E service auction mechanism design for other critical use cases, including edge intelligence.