paper-with-me

홈 › Papers

Selective Attention Improves Transformer

2024-10-03 · Yaniv Leviathan, Matan Kalman, Yossi Matias

Unneeded elements in the attention's context degrade performance. We introduce Selective Attention, a simple parameter-free change to the standard attention mechanism which reduces attention to unneeded elements. Selective attention improves language modeling performance in a variety of model sizes and context lengths. For example, a range of transformers trained with the language modeling objective on C4 with selective attention perform equivalently to standard transformers with ~2X more heads and parameters in their attention modules. Selective attention also allows decreasing the size of the attention's context buffer, leading to meaningful reductions in the memory and compute requirements during inference. For example, transformers with 100M parameters trained on C4 with context sizes of 512, 1,024, and 2,048 need 16X, 25X, and 47X less memory for their attention module, respectively, when equipped with selective attention, as those without selective attention, with the same validation perplexity.

📄 PDF Abstract BibTeX arXiv:2410.02703

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Mamba: Linear-Time Sequence Modeling with Selective State Spaces

2023-12-01 · Albert Gu, Tri Dao

Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module. Many subquadratic-time architectures such as…

2D Pose EstimationCommon Sense ReasoningComputational EfficiencyLanguage Modeling+5

The Art of Abstention: Selective Prediction and Error Regularization for Natural Language Processing

2021-08-01 · ACL 2021 5 · Ji Xin, Raphael Tang, YaoLiang Yu, Jimmy Lin

In selective prediction, a classifier is allowed to abstain from making predictions on low-confidence examples. Though this setting is interesting and important, selective prediction has rarely been examined in natural l…

Prediction

XAttnRes: Cross-Stage Attention Residuals for Medical Image Segmentation

2026-03-28 · Xinyu Liu, Qing Xu, Zhen Chen arxiv

In the field of Large Language Models (LLMs), Attention Residuals have recently demonstrated that learned, selective aggregation over all preceding layer outputs can outperform fixed residual connections. We propose Cros…

Medical Image Segmentation

Quantum-Optimized Selective State Space Model for Efficient Time Series Prediction

2025-08-29 · Stefan-Alexandru Jura, Mihai Udrescu, Alexandru Topirceanu arxiv

Long-range time series forecasting remains challenging, as it requires capturing non-stationary and multi-scale temporal dependencies while maintaining noise robustness, efficiency, and stability. Transformer-based archi…

Time Series ForecastingTime Series Prediction

Brain Tumor Classification using Vision Transformer with Selective Cross-Attention Mechanism and Feature Calibration

2024-06-25 · Mohammad Ali Labbaf Khaniki, Marzieh Mirzaeibonehkhater, Mohammad Manthouri, Elham Hasani

Brain tumor classification is a challenging task in medical image analysis. In this paper, we propose a novel approach to brain tumor classification using a vision transformer with a novel cross-attention mechanism. Our …

Brain Tumor ClassificationClassificationMedical Image Analysis