What question did this study set out to answer?

This research aims to systematically analyze the development and future directions of lightweight deep learning models in edge computing.

February 24, 2026Discover ComputingOpen Access

A comprehensive review of lightweight deep learning models for edge computing with future directions

View Full Paper

Ask AI

Bookmark

Authors

This review analyzes lightweight deep learning models for edge computing, highlighting future research pathways and implications.

This research aims to systematically analyze the development and future directions of lightweight deep learning models in edge computing.
Screened 543 articles from the Web of Science Core Collection based on PRISMA guidelines.
Conducted a combined bibliometric and systematic analysis approach.
Analyzed trends, themes, and future directions in lightweight deep learning models.
Field has experienced exponential growth in recent years.
Model compression is widely adopted as a foundational approach.
Neural architecture search has emerged as a mainstream design paradigm.
Knowledge distillation and lightweight Transformer architectures are important frontiers.
Key challenges include balancing accuracy, efficiency, and robustness.

Lai et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark