AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

SMYRF - Efficient Attention using Asymmetric Clustering

Giannis Daras, Nikita Kitaev, Augustus Odena, Alexandros G Dimakis

NeurIPS 2020 · Architectures and efficiency › Attention and transformers · approach: Linear attention approximations · 2 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
Replace dense attention with SMYRF at 50% memoryBERT base · GLUE devAvg.: $82.69$ -> $83.12$Improved
Reduce SMYRF-BERT memory to 25% and use cluster size 16 (ablation)BERT base · GLUE devAvg.: $83.12$ -> $81.74$Hurt
Replace full-length input with 32-token truncationBERT base · GLUE devAvg.: $82.69$ -> $73.56$Hurt
Replace dense attention with SMYRF at 50% memoryBERT base · IMDBaccuracy: $94.12\%$ -> $92.64\%$Hurt
Reduce SMYRF-BERT memory from 50% to 25% (ablation)BERT base · IMDBaccuracy: $92.64\%$ -> $92.52\%$Hurt
Reduce SMYRF-BERT memory from 25% to 12.5% (ablation)BERT base · IMDBaccuracy: $92.52\%$ -> $91.46$Hurt
Train with SMYRF and switch to dense attention for inferenceRoBERTa base · IMDBaccuracy: $93.72\%$ -> $94.62\%$Improved
Train with SMYRF and switch to dense attention for inferenceBERT base · IMDBaccuracy: $92.64\%$ -> $93.54\%$Improved
Replace SMYRF asymmetric hashing with E2LSH (ablation)SMYRF-RoBERTa · IMDB (3 epochs)accuracy: 93.7\% -> 89.3\%Hurt
Replace SMYRF hashing with cross-polytope LSH (ablation)SMYRF-RoBERTa · IMDB (3 epochs)accuracy: 93.7\% -> 88.7\%Hurt
Use 512-token context rather than Longformer's 4096-token contextSMYRF · Hyperpartisan News Detectionaccuracy: $94.8\%$ -> $97.2\%$Improved
Replace dense attention with SMYRF at 50% memoryBigGAN · BigGAN, ImageNetInception: $93.79 \pm 1.96$ -> $92.09 \pm 1.83$Hurt

Later papers that compared with this method

1 later accepted paper reports SMYRF 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