Attention Modules
Low-Rank Factorization-based Multi-Head Attention
Introduced by Mehta et al. in Low Rank Factorization for Compact Multi-Head Self-AttentionLow-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 |
|---|---|---|
| Language Modelling | 11 | 20.37% |
| Image Inpainting | 4 | 7.41% |
| In-Context Learning | 3 | 5.56% |
| Question Answering | 3 | 5.56% |
| Text Classification | 3 | 5.56% |
| Meta-Learning | 2 | 3.70% |
| Retrieval | 2 | 3.70% |
| Sentiment Analysis | 2 | 3.70% |
| Decoder | 1 | 1.85% |
Softmax
Tanh Activation
