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
PocketSphinx is a lightweight speech recognition engine, specifically tuned for handheld and mobile devices, though it works equally well on the desktop

molten A minimal, extensible, fast and productive API framework for Python 3. Changelog: https://moltenframework.com/changelog.html Community: https:/

3.2k Dec 28, 2022
In this project, we aim to achieve the task of predicting emojis from tweets. We aim to investigate the relationship between words and emojis.

Making Emojis More Predictable by Karan Abrol, Karanjot Singh and Pritish Wadhwa, Natural Language Processing (CSE546) under the guidance of Dr. Shad

Karanjot Singh 2 Jan 17, 2022
Stand-alone language identification system

langid.py readme Introduction langid.py is a standalone Language Identification (LangID) tool. The design principles are as follows: Fast Pre-trained

2k Jan 04, 2023
Binaural Speech Synthesis

Binaural Speech Synthesis This repository contains code to train a mono-to-binaural neural sound renderer. If you use this code or the provided datase

Facebook Research 135 Dec 18, 2022
Let Xiao Ai speakers control third-party devices

A stupid way to extend miot/xiaoai. Demo for Panasonic Bath Bully FV-RB20VL1 逆向 Panasonic Smart China,获得控制浴霸的请求信息(HTTP 请求),详见 apps/panasonic.py; 2. 通过

bin 14 Jul 07, 2022
This is Assignment1 code for the Web Data Processing System.

This is a Python program to Entity Linking by processing WARC files. We recognize entities from web pages and link them to a Knowledge Base(Wikidata).

3 Dec 04, 2022
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

ALBERT ***************New March 28, 2020 *************** Add a colab tutorial to run fine-tuning for GLUE datasets. ***************New January 7, 2020

Google Research 3k Dec 26, 2022
Dust model dichotomous performance analysis

Dust-model-dichotomous-performance-analysis Using a collated dataset of 90,000 dust point source observations from 9 drylands studies from around the

1 Dec 17, 2021
基于“Seq2Seq+前缀树”的知识图谱问答

KgCLUE-bert4keras 基于“Seq2Seq+前缀树”的知识图谱问答 简介 博客:https://kexue.fm/archives/8802 环境 软件:bert4keras=0.10.8 硬件:目前的结果是用一张Titan RTX(24G)跑出来的。 运行 第一次运行的时候,会给知

苏剑林(Jianlin Su) 65 Dec 12, 2022
edge-SR: Super-Resolution For The Masses

edge-SR: Super Resolution For The Masses Citation Pablo Navarrete Michelini, Yunhua Lu and Xingqun Jiang. "edge-SR: Super-Resolution For The Masses",

Pablo 40 Nov 10, 2022
基于pytorch+bert的中文事件抽取

pytorch_bert_event_extraction 基于pytorch+bert的中文事件抽取,主要思想是QA(问答)。 要预先下载好chinese-roberta-wwm-ext模型,并在运行时指定模型的位置。

西西嘛呦 31 Nov 30, 2022
This codebase facilitates fast experimentation of differentially private training of Hugging Face transformers.

private-transformers This codebase facilitates fast experimentation of differentially private training of Hugging Face transformers. What is this? Why

Xuechen Li 73 Dec 28, 2022
Quick insights from Zoom meeting transcripts using Graph + NLP

Transcript Analysis - Graph + NLP This program extracts insights from Zoom Meeting Transcripts (.vtt) using TigerGraph and NLTK. In order to run this

Advit Deepak 7 Sep 17, 2022
🕹 An esoteric language designed so that the program looks like the transcript of a Pokémon battle

PokéBattle is an esoteric language designed so that the program looks like the transcript of a Pokémon battle. Original inspiration and specification

Eduardo Correia 9 Jan 11, 2022
GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

GAP-text2SQL: Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training Code and model from our AAAI 2021 paper

Amazon Web Services - Labs 83 Jan 09, 2023
Python package for Turkish Language.

PyTurkce Python package for Turkish Language. Documentation: https://pyturkce.readthedocs.io. Installation pip install pyturkce Usage from pyturkce im

Mert Cobanov 14 Oct 09, 2022
Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis

MLP Singer Official implementation of MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis. Audio samples are available on our demo page.

Neosapience 103 Dec 23, 2022
A Survey of Natural Language Generation in Task-Oriented Dialogue System (TOD): Recent Advances and New Frontiers

A Survey of Natural Language Generation in Task-Oriented Dialogue System (TOD): Recent Advances and New Frontiers

Libo Qin 132 Nov 25, 2022
[ICLR 2021 Spotlight] Pytorch implementation for "Long-tailed Recognition by Routing Diverse Distribution-Aware Experts."

RIDE: Long-tailed Recognition by Routing Diverse Distribution-Aware Experts. by Xudong Wang, Long Lian, Zhongqi Miao, Ziwei Liu and Stella X. Yu at UC

Xudong (Frank) Wang 205 Dec 16, 2022
A Multi-modal Model Chinese Spell Checker Released on ACL2021.

ReaLiSe ReaLiSe is a multi-modal Chinese spell checking model. This the office code for the paper Read, Listen, and See: Leveraging Multimodal Informa

DaDa 106 Dec 29, 2022