Ghina Al-Atat

Ghina Al-Atat

Auto-generated profile, based on publicly available information

Ghina Al-Atat

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
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.

14 October 2024
Verified
Conference Paper
Open access
GAGhina Al-Atat
Ghina Al-Atat
PDPuranjay Datta
Puranjay Datta
SMSharayu Moharir
Sharayu Moharir
JCJaya Prakash Champati
Jaya Prakash Champati
Hierarchical Inference (HI) has emerged as a promising approach for efficient distributed inference between end devices deployed with small pre-trained Deep Learning (DL) models and edge/cloud servers running large DL models. Under HI, a device uses the local DL model to perform inference on the data samples it collects, and only the data samples on which this inference is likely to be incorrect are offloaded to a remote DL model running on the server. Thus, gauging the likelihood of incorrect local inference is key to implementing HI. A natural approach is to compute a confidence metric for the local DL inference and then use a threshold on this confidence metric to determine whether to offload or not. Recently, the HI online learning problem was studied to learn an optimal threshold for the confidence metric over a sequence of data samples collected over time. However, existing algorithms have computation complexity that grows with the number of rounds and do not exhibit a sub-linear regret bound. In this work, we propose the Hedge-HI algorithm and prove that it has [EQUATION] regret, where T is the number of rounds, and NT is the number of distinct confidence metric values observed till round T. Further, under a mild assumption, we propose Hedge-HI-Restart, which has an [EQUATION] regret bound with high probability and has a much lower computation complexity that grows sub-linearly in the number of rounds. Using runtime measurements on Raspberry Pi, we demonstrate that Hedge-HI-Restart has a runtime lower by order of magnitude and achieves cumulative loss close to that of the alternatives.