AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

AttCAT: Explaining Transformers via Attentive Class Activation Tokens

Yao Qiang, Deng Pan, Chengyin Li, Xin Li, Rhongho Jang, Dongxiao Zhu

NeurIPS 2022 · Architectures and efficiency › Attention and transformers · approach: Attention head and block redesign · 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
add self-attention weights to CAT (CAT -> AttCAT) (ablation)AttCAT · Amazon (BERT)AOPC: 0.409 -> 0.457Improved
add self-attention weights to CAT (CAT -> AttCAT) (ablation)AttCAT · IMDB (BERT)AOPC: 0.406 -> 0.528Improved
add self-attention weights to CAT (CAT -> AttCAT) (ablation)AttCAT · SST2 (BERT)AOPC: 0.352 -> 0.371Improved
AttCAT vs TransAttAttCAT · IMDB (BERT)LOdds: -2.137 -> -3.671Improved
AttCAT vs TransAttAttCAT · MNLI (BERT)AOPC: 0.130 -> 0.164Improved
AttCAT vs TransAttAttCAT · QQP (BERT)AOPC: 0.145 -> 0.139Hurt
AttCAT vs RawAtt on QQPAttCAT · QQP (BERT)LOdds: 0.149 -> 0.073Improved
AttCAT vs best baseline confidenceAttCAT · Kendall-tau, SST2Kendall-tau: 0.101 -> 0.018Improved
AttCAT vs CAT confidence on QQPAttCAT · Kendall-tau, QQPKendall-tau: 0.222 -> 0.349Hurt
summing layer impact scores instead of rollout (ablation)AttCAT · BERT layer heatmapimpact scoreImproved
attention-based methods (RawAtt, Rollout) vs gradient methodsRawAtt/Rollout · 6 datasetsAOPC and LOddsHurt

Later papers that compared with this method

1 later accepted paper reports AttCAT 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