AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

The Strong Lottery Ticket Hypothesis for Multi-Head Attention Mechanisms

Hikari Otsuka, Daiki Chijiwa, Yasuyuki Okoshi, Daichi Fujiki, Susumu Takeuchi, Masato Motomura

AAAI 2026 · Architectures and efficiency › Attention and transformers · approach: Attention head mechanisms · 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
add query/key weight scaling by n_K^(1/4) at initialization (ablation)SLT search with edge-popup in GPT-2 · WikiText-103validation lossImproved
increase query/key weight scale beyond n_K^(1/4) (ablation)SLT search with edge-popup in GPT-2 · WikiText-103validation lossHurt
increase source hidden dimension n_KSLT in random MHA · Synthetic angular velocityapproximation error: epsilon = 0.8 exp(-0.06 n_K)Improved
increase input sequence length TSLT in random MHA · Synthetic angular velocityapproximation errorNo clear effect
increase number of transformer blocks with shared decay rateSLT in random transformer · Synthetic angular velocityapproximation errorImproved

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