AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

A Study on Encodings for Neural Architecture Search

Colin White, Willie Neiswanger, Sam Nolen, Yash Savani

NeurIPS 2020 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use adjacency encoding instead of path encoding in neural predictor (ablation)neural predictor · NASBench-101 outside search spacetest error top 10 avg.: 6.616 -> 6.454Improved
use categorical adjacency instead of adjacency encoding (ablation)neural predictor · NASBench-101 outside search spacetest error top 10 avg.: 6.454 -> 8.155Hurt
truncate path encoding (ablation)neural predictor · NASBench-101 outside search spacetest error top 10 avg.: 6.616 -> 6.712Hurt
make path encoding categorical (ablation)neural predictor · NASBench-101 outside search spacetest error top 10 avg.: 6.616 -> 6.939Hurt
truncate path encoding from 364 to 40 paths (ablation)regularized evolution · NASBench-101test errorImproved
truncate path encoding from 364 to 40 paths (ablation)other NAS algorithms with path encoding · NASBench-101test errorNo clear effect
use path encodings instead of adjacency matrix encodings for the predictor model (ablation)BO and neural predictor · NASBench-101predictor error / search performanceImproved
use adjacency matrix encodings instead of path encodings for random sampling and perturbation (ablation)Random Search, regularized evolution, local search · NASBench-101test errorImproved
use path encoding instead of GCN or VAE (ablation)neural predictor · NASBench-101mean absolute errorImproved
combine best encodings for each subroutine (ablation)BANANAS · NASBench-101test errorImproved
truncate one-hot adjacency encoding from 31 bits to 0 bits versus truncating path encoding (ablation)regularized evolution · NASBench-101test errorMixed
group architectures by path encoding equivalence class (ablation)path encoding · NASBench-101std of accuracy (%): 5.55 -> 0.353Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy