TL;DR
This paper introduces a task-aware neural architecture search framework that leverages a dictionary of base models and a gradient-based search algorithm to efficiently discover optimal architectures tailored to specific tasks.
Contribution
It presents a novel adaptive search space construction method using task similarity and a gradient-based algorithm for efficient architecture discovery.
Findings
Effective in generating task-specific neural architectures
Reduces training time compared to traditional NAS methods
Demonstrates superior performance on benchmark tasks
Abstract
The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
