AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

AutoAttend: Automated Attention Representation Search

Chaoyu Guan, Xin Wang, Wenwu Zhu

ICML 2021 · Architectures and efficiency › Neural architecture search · approach: AutoML pipeline search · 11 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
add attention layer (attention representation search) to the search space (ablation)NAS search space for SST · SST validationaccuracy [%]: 81.15 -> 81.68Improved
add attention layer to the search space (ablation)NAS search space for Cora · Cora validationaccuracy [%]: 81.80 -> 82.96Improved
add attention layer to the search space (ablation)NAS search space for CiteSeer · CiteSeer validationaccuracy [%]: 72.18 -> 72.90Improved
add attention layer to the search space (ablation)NAS search space for PubMed · PubMed validationaccuracy [%]: 81.04 -> 81.04No clear effect
full context-aware parameter sharing (source and target context) vs no context (ablation)supernet parameter sharing for SST · SST validationaccuracy [%]: 68.68 -> 69.40Improved
full context-aware parameter sharing vs no context (ablation)supernet parameter sharing for Cora · Cora validationaccuracy [%]: 77.09 -> 78.61Improved
full context-aware parameter sharing vs no context (ablation)supernet parameter sharing for PubMed · PubMed validationaccuracy [%]: 72.72 -> 77.72Improved
source-only context (SC) vs no context (ablation)supernet parameter sharing · SST/Cora/CiteSeer/PubMed validationaccuracy [%]: SST 68.68->68.96, Cora 77.09->77.81, CiteSeer 63.68->63.62, PubMed 72.72->73.31Mixed
searched attention representation (AutoAttend) vs previous NAS on text classificationtransferred sentence encoder · SST and transferred NLP datasetsaccuracy [%]: SST +1.20 over TextNAS (53.71 vs 52.51); transfer gains under 1.00%Improved
searched attention representation vs hand-crafted SOTA on graph node classificationGRL transductive and inductive tasks · Cora, CiteSeer, PubMed, PPIaccuracy / F1: Cora +0.3, PubMed +0.4, PPI +0.1 over best baseline; CiteSeer 73.0 vs AGNN 73.8Mixed
searched attention representation vs hand-crafted SOTA on text classificationtransferred sentence encoder · YELP and AGaccuracy [%]: AG 93.53 vs 93.20 (GELE); YELP 66.82 vs 67.00 (GELE)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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