Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.

Last update: Dec 19, 2022

Overview

Linear Transformers Are Secretly Fast Weight Programmers

This repository contains the code accompanying the paper Linear Transformers Are Secretly Fast Weight Programmers which is published at ICML'21. It also contains the logs of all synthetic experiments.

Synthetic Experiments

Requirements

$ cat req.txt 
jupyter==1.0.0
pandas==1.0.1
seaborn==0.10.0
torch==1.6.0
matplotlib==3.1.3
numpy==1.17.2

pip3 install -r req.txt

Rerun Experiments

Logs are provided in the synthetic/logs folder. The files in that folder are a result of running the following commands:

Setting 1 (capacity):

python3 main.py --begin=20 --end=600 --step=20 --attn_name=softmax --update_rule=sum
python3 main.py --begin=20 --end=600 --step=20 --attn_name=linear --update_rule=sum
python3 main.py --begin=20 --end=600 --step=20 --attn_name=dpfp --attn_arg=1 --update_rule=sum
python3 main.py --begin=20 --end=600 --step=20 --attn_name=dpfp --attn_arg=2 --update_rule=sum

python3 main.py --begin=20 --end=600 --step=20 --attn_name=dpfp --attn_arg=3 --update_rule=sum
python3 main.py --begin=20 --end=600 --step=20 --attn_name=favor --attn_arg=64 --update_rule=sum
python3 main.py --begin=20 --end=600 --step=20 --attn_name=favor --attn_arg=128 --update_rule=sum
python3 main.py --begin=20 --end=600 --step=20 --attn_name=favor --attn_arg=512 --update_rule=sum

Setting 2 (update rule):

python3 main.py --begin=20 --end=200 --step=20 --attn_name=dpfp --attn_arg=1 --update_rule=sum --replace
python3 main.py --begin=20 --end=200 --step=20 --attn_name=dpfp --attn_arg=1 --update_rule=ours --replace
python3 main.py --begin=20 --end=200 --step=20 --attn_name=tanh --update_rule=fwm --replace
python3 main.py --begin=20 --end=200 --step=20 --attn_name=dpfp --attn_arg=1 --update_rule=fwm --replace

python3 main.py --begin=20 --end=200 --step=20 --attn_name=dpfp --attn_arg=2 --update_rule=ours --replace
python3 main.py --begin=20 --end=200 --step=20 --attn_name=linear --update_rule=ours --replace
python3 main.py --begin=20 --end=200 --step=20 --attn_name=favor --attn_arg=64 --update_rule=ours --replace
python3 main.py --begin=20 --end=200 --step=20 --attn_name=favor --attn_arg=128 --update_rule=ours --replace

Generate figures from the logs using the following notebooks:

synthetic/setting1_generate_figure.ipynb
synthetic/setting2_generate_figure.ipynb

Language Modelling & Machine Translation

The toolkit and scripts for language modeling experiments can be found at IDSIA/lmtool-fwms.

For machine translation experiments, we ported the different attention functions implemented in the language modeling toolkit to the multi-head attention implementation in FAIRSEQ.

Citation

@inproceedings{schlag2021linear,
      title={Linear Transformers Are Secretly Fast Weight Programmers}, 
      author={Imanol Schlag and Kazuki Irie and J\"urgen Schmidhuber},
      booktitle={Proc. Int. Conf. on Machine Learning (ICML)},
      address = {Virtual only},
      month = jul,
      year={2021}
}

Official code repository of the paper Linear Transformers Are Secretly Fast Weight Programmers.

Related tags

Overview

Linear Transformers Are Secretly Fast Weight Programmers

Synthetic Experiments

Requirements

Rerun Experiments

Language Modelling & Machine Translation

Citation

Owner

Imanol Schlag

Example code for "Real-World Natural Language Processing"

Klexikon: A German Dataset for Joint Summarization and Simplification

Baseline code for Korean open domain question answering(ODQA)

PyTorch Implementation of VAENAR-TTS: Variational Auto-Encoder based Non-AutoRegressive Text-to-Speech Synthesis.

p-tuning for few-shot NLU task

ProtFeat is protein feature extraction tool that utilizes POSSUM and iFeature.

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

[EMNLP 2021] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.

Final Project Bootcamp Zero

This repository contains (not all) code from my project on Named Entity Recognition in philosophical text

Predicting the usefulness of reviews given the review text and metadata surrounding the reviews.

Code release for NeX: Real-time View Synthesis with Neural Basis Expansion

Finding Label and Model Errors in Perception Data With Learned Observation Assertions

Multi-Scale Temporal Frequency Convolutional Network With Axial Attention for Speech Enhancement

Code for ACL 2020 paper "Rigid Formats Controlled Text Generation"

A look-ahead multi-entity Transformer for modeling coordinated agents.

A natural language modeling framework based on PyTorch

DensePhrases provides answers to your natural language questions from the entire Wikipedia in real-time

Text editor on python to convert english text to malayalam(Romanization/Transiteration).

RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).