Toward inference delivery networks: distributing machine learning with optimality guarantees - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE/ACM Transactions on Networking Year : 2023

Toward inference delivery networks: distributing machine learning with optimality guarantees

Abstract

An increasing number of applications rely on complex inference tasks that are based on machine learning (ML). Currently, there are two options to run such tasks: either they are served directly by the end device (e.g., smartphones, IoT equipment, smart vehicles), or offloaded to a remote cloud. Both options may be unsatisfactory for many applications: local models may have inadequate accuracy, while the cloud may fail to meet delay constraints. In this paper, we present the novel idea of inference delivery networks (IDNs), networks of computing nodes that coordinate to satisfy ML inference requests achieving the best trade-off between latency and accuracy. IDNs bridge the dichotomy between device and cloud execution by integrating inference delivery at the various tiers of the infrastructure continuum (access, edge, regional data center, cloud). We propose a distributed dynamic policy for ML model allocation in an IDN by which each node dynamically updates its local set of inference models based on requests observed during the recent past plus limited information exchange with its neighboring nodes. Our policy offers strong performance guarantees in an adversarial setting and shows improvements over greedy heuristics with similar complexity in realistic scenarios.
Fichier principal
Vignette du fichier
2105.02510 (5).pdf (1.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04385717 , version 1 (10-01-2024)

Licence

Attribution

Identifiers

Cite

Tareq Si Salem, Gabriele Castellano, Giovanni Neglia, Fabio Pianese, Andrea Araldo. Toward inference delivery networks: distributing machine learning with optimality guarantees. IEEE/ACM Transactions on Networking, 2023, pp.1. ⟨10.1109/TNET.2023.3305922⟩. ⟨hal-04385717⟩
15 View
18 Download

Altmetric

Share

Gmail Facebook X LinkedIn More