• español
    • English
  • Login
  • español 
    • español
    • English
  • Tipos de Publicaciones
    • bookbook partconference objectdoctoral thesisjournal articlemagazinemaster thesispatenttechnical documentationtechnical report
Ver ítem 
  •   IMDEA Networks Principal
  • Ver ítem
  •   IMDEA Networks Principal
  • Ver ítem
JavaScript is disabled for your browser. Some features of this site may not work without it.

The Case for Hierarchical Deep Learning Inference at the Network Edge

Compartir
Ficheros
3597062.3597278.pdf (929.5Kb)
Identificadores
URI: https://hdl.handle.net/20.500.12761/1720
Metadatos
Mostrar el registro completo del ítem
Autor(es)
Al Atat, Ghina; Fresa, Andrea; Behera, Adarsh Prasad; Moothedath, Vishnu Narayanan; Gross, James; Champati, Jaya Prakash
Fecha
2023-06-21
Resumen
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.
Compartir
Ficheros
3597062.3597278.pdf (929.5Kb)
Identificadores
URI: https://hdl.handle.net/20.500.12761/1720
Metadatos
Mostrar el registro completo del ítem

Listar

Todo IMDEA NetworksPor fecha de publicaciónAutoresTítulosPalabras claveTipos de contenido

Mi cuenta

Acceder

Estadísticas

Ver Estadísticas de uso

Difusión

emailContacto person Directorio wifi Eduroam rss_feed Noticias
Iniciativa IMDEA Sobre IMDEA Networks Organización Memorias anuales Transparencia
Síguenos en:
Comunidad de Madrid

UNIÓN EUROPEA

Fondo Social Europeo

UNIÓN EUROPEA

Fondo Europeo de Desarrollo Regional

UNIÓN EUROPEA

Fondos Estructurales y de Inversión Europeos

© 2021 IMDEA Networks. | Declaración de accesibilidad | Política de Privacidad | Aviso legal | Política de Cookies - Valoramos su privacidad: ¡este sitio no utiliza cookies!