AutoCoMet: Smart Neural Architecture Search via Co-Regulated Shaping Reinforcement

TL;DR

AutoCoMet is an advanced neural architecture search framework that efficiently designs optimized deep learning models for diverse mobile hardware and tasks, significantly reducing search time while maintaining high fidelity.

Contribution

It introduces a co-regulated shaping reinforcement controller and hardware meta-behavior predictor for fast, context-aware NAS applicable to various multi-criteria optimization scenarios.

Findings

Achieves ~3x faster NAS compared to existing methods.

Provides high-fidelity hardware-aware architecture optimization.

Adapts to diverse device hardware and task contexts effectively.

Abstract

Designing suitable deep model architectures, for AI-driven on-device apps and features, at par with rapidly evolving mobile hardware and increasingly complex target scenarios is a difficult task. Though Neural Architecture Search (NAS/AutoML) has made this easier by shifting paradigm from extensive manual effort to automated architecture learning from data, yet it has major limitations, leading to critical bottlenecks in the context of mobile devices, including model-hardware fidelity, prohibitive search times and deviation from primary target objective(s). Thus, we propose AutoCoMet that can learn the most suitable DNN architecture optimized for varied types of device hardware and task contexts, ~ 3x faster. Our novel co-regulated shaping reinforcement controller together with the high fidelity hardware meta-behavior predictor produces a smart, fast NAS framework that adapts to context via a generalized formalism for any kind of multi-criteria optimization.