Andrea Fresa

Andrea Fresa

Auto-generated profile, based on publicly available information

Andrea Fresa

IMDEA Networks Institute, Madrid, Spain

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
19 April 2023 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
AFAndrea Fresa
Andrea Fresa
JCJaya Prakash Champati
Jaya Prakash Champati
With the emergence of edge computing, the problem of offloading jobs between an Edge Device (ED) and an Edge Server (ES) received significant attention in the past. Motivated by the fact that an increasing number of applications are using Machine Learning (ML) inference from the data samples collected at the EDs, we study the problem of offloading inference jobs by considering the following novel aspects: 1) in contrast to a typical computational job, the processing time of an inference job depends on the size of the ML model, and 2) recently proposed Deep Neural Networks (DNNs) for resource-constrained devices provide the choice of scaling down the model size by trading off the inference accuracy. Considering that multiple ML models are available at the ED, and a powerful ML model is available at the ES, we formulate an Integer Linear Programming (ILP) problem with the objective of maximizing the total inference accuracy of $n$ data samples at the ED subject to a time constraint $T$ on the makespan. Noting that the problem is NP-hard, we propose an approximation algorithm Accuracy Maximization using LP-Relaxation and Rounding (AMR $^{2}$ ) and prove that it results in a makespan at most $\text{2}T$ and achieves a total accuracy that is lower by a small constant from the optimal total accuracy implying that AMR $^{2}$ is asymptotically optimal. Further, if the data samples are identical we propose Accuracy Maximization using Dynamic Programming (AMDP), an optimal pseudo-polynomial time algorithm. Furthermore, we extend AMR $^{2}$ for the case of multiple ESs, where each ES is equipped with a powerful ML model. As proof of concept, we implemented AMR $^{2}$ on a Raspberry Pi, equipped with MobileNets, that is connected to a server equipped with ResNet, and studied the total accuracy and makespan performance of AMR $^{2}$ for image classification.

18 June 2023
Verified
Conference Paper
Open access
GAGhina Al-Atat
Ghina Al-Atat
AFAndrea Fresa
Andrea Fresa
ABAdarsh Prasad Behera
Adarsh Prasad Behera
VMVishnu Narayanan Moothedath
Vishnu Narayanan Moothedath
JGJames Gross
James Gross
JCJaya Prakash Champati
Jaya Prakash Champati
Resource-constrained Edge Devices (EDs), e.g., IoT sensors and microcontroller units, are expected to make intelligent decisions using Deep Learning (DL) inference at the edge of the network. Toward this end, developing tinyML models is an area of active research - DL models with reduced computation and memory storage requirements - that can be embedded on these devices. However, tinyML models have lower inference accuracy. On a different front, DNN partitioning and inference offloading techniques were studied for distributed DL inference between EDs and Edge Servers (ESs). In this paper, we explore Hierarchical Inference (HI), a novel approach proposed in [19] for performing distributed DL inference at the edge. Under HI, for each data sample, an ED first uses a local algorithm (e.g., a tinyML model) for inference. Depending on the application, if the inference provided by the local algorithm is incorrect or further assistance is required from large DL models on edge or cloud, only then the ED offloads the data sample. At the outset, HI seems infeasible as the ED, in general, cannot know if the local inference is sufficient or not. Nevertheless, we present the feasibility of implementing HI for image classification applications. We demonstrate its benefits using quantitative analysis and show that HI provides a better trade-off between offloading cost, throughput, and inference accuracy compared to alternate approaches.