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

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}
}
Owner
Imanol Schlag
Imanol Schlag
Official codebase for Can Wikipedia Help Offline Reinforcement Learning?

Official codebase for Can Wikipedia Help Offline Reinforcement Learning?

Machel Reid 82 Dec 19, 2022
A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

420 Dec 28, 2022
A natural language modeling framework based on PyTorch

Overview PyText is a deep-learning based NLP modeling framework built on PyTorch. PyText addresses the often-conflicting requirements of enabling rapi

Meta Research 6.4k Jan 08, 2023
Artificial Conversational Entity for queries in Eulogio "Amang" Rodriguez Institute of Science and Technology (EARIST)

πŸ€– Coeus - EARIST A.C.E πŸ’¬ Coeus is an Artificial Conversational Entity for queries in Eulogio "Amang" Rodriguez Institute of Science and Technology,

Dids Irwyn Reyes 3 Oct 14, 2022
πŸš€Clone a voice in 5 seconds to generate arbitrary speech in real-time

English | δΈ­ζ–‡ Features 🌍 Chinese supported mandarin and tested with multiple datasets: aidatatang_200zh, magicdata, aishell3, data_aishell, and etc. ?

Vega 25.6k Dec 31, 2022
All the code I wrote for Overwatch-related projects that I still own the rights to.

overwatch_shit.zip This is (eventually) going to contain all the software I wrote during my five-year imprisonment stay playing Overwatch. I'll be add

zkxjzmswkwl 2 Dec 31, 2021
Chinese segmentation library

What is loso? loso is a Chinese segmentation system written in Python. It was developed by Victor Lin ( Fang-Pen Lin 82 Jun 28, 2022

An assignment on creating a minimalist neural network toolkit for CS11-747

minnn by Graham Neubig, Zhisong Zhang, and Divyansh Kaushik This is an exercise in developing a minimalist neural network toolkit for NLP, part of Car

Graham Neubig 63 Dec 29, 2022
LeBenchmark: a reproducible framework for assessing SSL from speech

LeBenchmark: a reproducible framework for assessing SSL from speech

11 Nov 30, 2022
Deep Learning Topics with Computer Vision & NLP

Deep learning Udacity Course Deep Learning Topics with Computer Vision & NLP for the AWS Machine Learning Engineer Nanodegree Program Tasks are mostly

Simona Mircheva 1 Jan 20, 2022
ACL22 paper: Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost

Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost LOVE is accpeted by ACL22 main conference as a long pape

Lihu Chen 32 Jan 03, 2023
Deep learning for NLP crash course at ABBYY.

Deep NLP Course at ABBYY Deep learning for NLP crash course at ABBYY. Suggested textbook: Neural Network Methods in Natural Language Processing by Yoa

Dan Anastasyev 597 Dec 18, 2022
🌐 Translation microservice powered by AI

Dot Translate 🌐 A microservice for quick and local translation using A.I. This service starts a local webserver used for neural machine translation.

Dot HQ 48 Nov 22, 2022
λ‰΄μŠ€ 도메인 μ§ˆμ˜μ‘λ‹΅ μ‹œμŠ€ν…œ (21-1ν•™κΈ° μ‘Έμ—… ν”„λ‘œμ νŠΈ)

λ‰΄μŠ€ 도메인 μ§ˆμ˜μ‘λ‹΅ μ‹œμŠ€ν…œ λ³Έ ν”„λ‘œμ νŠΈλŠ” λ‰΄μŠ€κΈ°μ‚¬μ— λŒ€ν•œ μ§ˆμ˜μ‘λ‹΅ μ„œλΉ„μŠ€ λ₯Ό μ œκ³΅ν•˜κΈ° μœ„ν•΄μ„œ μ§„ν–‰ν•œ ν”„λ‘œμ νŠΈμž…λ‹ˆλ‹€. μ•½ 3κ°œμ›”κ°„ ( 21. 03 ~ 21. 05 ) μ§„ν–‰ν•˜μ˜€μœΌλ©° Transformer 아킀텍쳐 기반의 Encoderλ₯Ό μ‚¬μš©ν•˜μ—¬ ν•œκ΅­μ–΄ μ§ˆμ˜μ‘λ‹΅ λ°μ΄ν„°μ…‹μœΌλ‘œ

TaegyeongEo 4 Jul 08, 2022
Using BERT-based models for toxic span detection

SemEval 2021 Task 5: Toxic Spans Detection: Task: Link to SemEval-2021: Task 5 Toxic Span Detection is https://competitions.codalab.org/competitions/2

Ravika Nagpal 1 Jan 04, 2022
An open source library for deep learning end-to-end dialog systems and chatbots.

DeepPavlov is an open-source conversational AI library built on TensorFlow, Keras and PyTorch. DeepPavlov is designed for development of production re

Neural Networks and Deep Learning lab, MIPT 6k Dec 31, 2022
Protein Language Model

ProteinLM We pretrain protein language model based on Megatron-LM framework, and then evaluate the pretrained model results on TAPE (Tasks Assessing P

THUDM 77 Dec 27, 2022
Meta learning algorithms to train cross-lingual NLI (multi-task) models

Meta learning algorithms to train cross-lingual NLI (multi-task) models

M.Hassan Mojab 4 Nov 20, 2022
A PyTorch Implementation of End-to-End Models for Speech-to-Text

speech Speech is an open-source package to build end-to-end models for automatic speech recognition. Sequence-to-sequence models with attention, Conne

Awni Hannun 647 Dec 25, 2022
A Lightweight NLP Data Loader for All Deep Learning Frameworks in Python

LineFlow: Framework-Agnostic NLP Data Loader in Python LineFlow is a simple text dataset loader for NLP deep learning tasks. LineFlow was designed to

TofuNLP 177 Jan 04, 2023