Attention Modules

Low-Rank Factorization-based Multi-Head Attention

Introduced by Mehta et al. in Low Rank Factorization for Compact Multi-Head Self-Attention

Low-Rank Factorization-based Multi-head Attention Mechanism, or LAMA, is a type of attention module that uses low-rank factorization to reduce computational complexity. It uses low-rank bilinear pooling to construct a structured sentence representation that attends to multiple aspects of a sentence.

Source: Low Rank Factorization for Compact Multi-Head Self-Attention

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
LAMA 17 37.78%
Language Modelling 8 17.78%
Text Classification 3 6.67%
Meta-Learning 2 4.44%
Question Answering 2 4.44%
Sentiment Analysis 2 4.44%
Image Inpainting 1 2.22%
Anomaly Detection 1 2.22%
Image Generation 1 2.22%

Categories