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

HF's ML for Audio study group

GNES enables large-scale index and semantic search for text-to-text, image-to-image, video-to-video and any-to-any content form

The code from the whylogs workshop in DataTalks.Club on 29 March 2022

PyTorch implementation and pretrained models for XCiT models. See XCiT: Cross-Covariance Image Transformer

PyJPBoatRace: Python-based Japanese boatrace tools 🚤

Paradigm Shift in NLP - "Paradigm Shift in Natural Language Processing".

Semantic search for quotes.

Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE

Text-Based zombie apocalyptic decision-making game in Python

Code to reprudece NeurIPS paper: Accelerated Sparse Neural Training: A Provable and Efficient Method to Find N:M Transposable Masks

Lumped-element impedance calculator and frequency-domain plotter.

A Neural Language Style Transfer framework to transfer natural language text smoothly between fine-grained language styles like formal/casual, active/passive, and many more. Created by Prithiviraj Damodaran. Open to pull requests and other forms of collaboration.

Understanding the Difficulty of Training Transformers

The RWKV Language Model

Analyse japanese ebooks using MeCab to determine the difficulty level for japanese learners

Twitter bot that uses NLP models to summarize news articles referenced in a user's twitter timeline

Code for using and evaluating SpanBERT.

Rhythm-Finder is a unsupervised ML driven python powered web-application that can find the songs that suits you.

TunBERT is the first release of a pre-trained BERT model for the Tunisian dialect using a Tunisian Common-Crawl-based dataset.

PyTorch implementation of the paper: Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding