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

Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering

Residual2Vec: Debiasing graph embedding using random graphs

Kurumi ChatBot

Machine Learning Course Project, IMDB movie review sentiment analysis by lstm, cnn, and transformer

Python functions for summarizing and improving voice dictation input.

This is a general repo that helps you develop fast/effective NLP classifiers using Huggingface

Graphical user interface for Argos Translate

🐍💯pySBD (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box.

A program that uses real statistics to choose the best times to bet on BloxFlip's crash gamemode

nlabel is a library for generating, storing and retrieving tagging information and embedding vectors from various nlp libraries through a unified interface.

Code to use Augmented Shapiro Wilks Stopping, as well as code for the paper "Statistically Signifigant Stopping of Neural Network Training"

Chinese NewsTitle Generation Project by GPT2.带有超级详细注释的中文GPT2新闻标题生成项目。

Tool to add main subject to items on Wikidata using a WMFs CirrusSearch for named entity recognition or a manually supplied list of QIDs

A Plover python dictionary allowing for consistent symbol input with specification of attachment and capitalisation in one stroke.

Conditional Transformer Language Model for Controllable Generation

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

This is a MD5 password/passphrase brute force tool

BERT, LDA, and TFIDF based keyword extraction in Python

Shared code for training sentence embeddings with Flax / JAX

I can help you convert your images to pdf file.