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

Categories