AI Paper Atlas

Research map / Architectures and efficiency / Attention and transformers

Self-attention with Functional Time Representation Learning

Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, Kannan Achan

NeurIPS 2019 · Architectures and efficiency › Attention and transformers · approach: Sparse and structured attention · 32 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 positional encoding with Mercer time embedding (ablation)self-attention · Stack Overflowaccuracy: 44.03 -> 46.83Improved
replace positional encoding with Mercer time embedding (ablation)self-attention · MovieLens-1mNDCG@10: 59.05 -> 61.67Improved
replace positional encoding with Mercer time embedding (ablation)self-attention · Walmart.comHit@10: 12.49 -> 14.94Improved
replace positional encoding with Bochner Non-para time embedding (ablation)self-attention · Walmart.comHit@10: 12.49 -> 13.16Improved
replace positional encoding with Bochner Normal time embedding (ablation)self-attention · Walmart.comHit@10: 12.49 -> 7.66Hurt
replace positional encoding with Bochner Normal time embedding (ablation)self-attention · Stack Overflowaccuracy: 44.03 -> 44.89No clear effect
replace positional encoding with Bochner Inv CDF time embedding (ablation)self-attention · Stack Overflowaccuracy: 44.03 -> 44.67No clear effect
replace positional encoding with Bochner Inv CDF time embedding (ablation)self-attention · Walmart.comHit@10: 12.49 -> 12.77No clear effect
replace positional encoding with Mercer time embedding (ablation)self-attention · MovieLens-1mHit@10: 82.45 -> 82.92No clear effect
use larger Fourier degree k for Mercer embedding at fixed d (ablation)Mercer time embedding · MovieLens-1mHit@10Hurt

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