AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

TA-GATES: An Encoding Scheme for Neural Network Architectures

Xuefei Ning, Zixuan Zhou, Junbo Zhao, Tianchen Zhao, Yiping Deng, Changcheng Tang, Shuang Liang, Huazhong Yang, Yu Wang

NeurIPS 2022 · Architectures and efficiency › Neural architecture search · approach: Latency-aware architecture search · 0 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 TA-GATES encoder instead of GATESGATES · NB101, 1% trainingKendall's Tau: 0.6321 -> 0.6686Improved
use TA-GATES encoder instead of GATESGATES · NB201, 0.1% trainingKendall's Tau: 0.4309 -> 0.5382Improved
use TA-GATES encoder instead of GATESGATES · NB201, 0.5% trainingKendall's Tau: 0.6702 -> 0.6707No clear effect
use TA-GATES encoder instead of GATESGATES · NDS ENAS, 100% trainingKendall's Tau: 0.6467 -> 0.6683Improved
add symmetry breaking (Add) to TA-GATES (ablation)TA-GATES (None) · NB101, 5% trainingKendall's Tau: 0.7581 -> 0.7744Improved
add symmetry breaking (Add) to TA-GATES (ablation)TA-GATES (None) · NB301, 1% trainingKendall's Tau: 0.6182 -> 0.6351Improved
add symmetry breaking (Add) to TA-GATES (ablation)TA-GATES (None) · NB201, 0.5% trainingKendall's Tau: 0.6838 -> 0.6707Hurt
use Random symmetry breaking instead of none (ablation)TA-GATES (None) · NB101, 1% trainingKendall's Tau: 0.6510 -> 0.6425Hurt
use Concat symmetry breaking instead of none (ablation)TA-GATES (None) · NB101, 1% trainingKendall's Tau: 0.6510 -> 0.6585Improved
use Add instead of Concat symmetry breaking (ablation)TA-GATES · NB101, 1% trainingKendall's Tau: 0.6585 -> 0.6686Improved
TA-GATES with half+final signals vs Multi-GATES (half accuracy)Multi-GATES · NB101, 5% training, half accuracyKendall's Tau: 0.2912 -> 0.4615Improved
TA-GATES with half+final signals vs Multi-GATES (final accuracy)Multi-GATES · NB101, 5% training, final accuracyKendall's Tau: 0.3341 -> 0.5850Improved

Later papers that compared with this method

1 later accepted paper reports TAGATES as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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