Official PyTorch implementation of Time-aware Large Kernel (TaLK) Convolutions (ICML 2020)

Last update: Dec 07, 2022

Overview

Time-aware Large Kernel (TaLK) Convolutions (Lioutas et al., 2020)

This repository contains the source code, pre-trained models, as well as instructions to reproduce results for our paper Time-aware Large Kernel Convolutions (ICML 2020).

TaLK Convolutions is a sequence modeling method that uses an adaptive convolution operation that learns to predict the size of a summation kernel instead of using a fixed-sized learnable kernel matrix. It utilizes a fast parallelized implementation of the summed-area table, also known as the integral image operation, to efficiently calculate the convolution output that uses the summation kernel. We generate relative offsets for each timestep of the input sequence, which are used to adaptively expand the size of the summation kernel conditioned on the input. This method yields a time complexity of O(n), effectively making the sequence encoding process linear to the number of tokens.

Video Presentation:

Citation:

@inproceedings{lioutas2020timeaware,
    author={Vasileios Lioutas and Yuhong Guo},
    title={Time-aware Large Kernel Convolutions},
    booktitle={Proceedings of the 37th International Conference on Machine Learning (ICML)},
    year={2020}
}

Setup

Requirements

PyTorch version >= 1.3.1
fairseq version >= 0.10.1
Python version >= 3.6
CUDA >= 10.1
NVIDIA's apex library (for mixed-precision training)

Clone this repository

git clone https://github.com/lioutasb/TaLKConvolutions.git
cd TaLKConvolutions

Efficient CUDA Kernels

In order to support the parallelization of TaLK Convolutions, we have developed our own CUDA primitives. To install the kernels, use the commands below. We tested compiling the kernels using CUDA 10.1 but if a future CUDA release does not work, please feel free to open an issue.

cd talkconv/talkconv_module/
python setup.py install

We are welcoming contributions from experienced CUDA developers regarding making the CUDA kernels more efficient.

Translation

Pre-trained models

Dataset	Model	Prepared test set
IWSLT14 German-English	download (.pt)	IWSLT14 test: download (.zip)
WMT16 English-German	download (.pt)	newstest2014: download (.zip)
WMT14 English-French	download (.pt)	newstest2014: download (.zip)

Preprocessing the training datasets

Please follow the instructions https://github.com/pytorch/fairseq/blob/master/examples/translation/README.md to preprocess the data.

IWSLT14 De-En

Training and evaluating TaLK Convolutions on a single GPU:

# Training
SAVE="checkpoints/talkconv_iwslt_deen"
mkdir -p $SAVE

CUDA_VISIBLE_DEVICES=0 \
fairseq-train data-bin/iwslt14.tokenized.de-en \
    --user-dir talkconv/talkconv_fairseq \
    --arch talkconv_iwslt_de_en \
    --optimizer adam  --fp16 --lr 0.0005 \
    --source-lang de --target-lang en --max-tokens 4000 \
    --min-lr '1e-09' --weight-decay 0.0001 \
    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
    --lr-scheduler inverse_sqrt \
    --dropout 0.3 --attention-dropout 0.1 --weight-dropout 0.1  \
    --max-update 85000 --warmup-updates 4000 --warmup-init-lr '1e-07' \
    --adam-betas '(0.9, 0.98)' --left-pad-source "False" --max-epoch 52 --seed 1024 \
    --save-dir $SAVE 

python utils/average_checkpoints.py --inputs $SAVE \
    --num-epoch-checkpoints 10 --output "${SAVE}/model.pt"

# Evaluation
fairseq-generate data-bin/iwslt14.tokenized.de-en --user-dir talkconv/talkconv_fairseq \
    --path "${SAVE}/model.pt" \
    --batch-size 128 --beam 5 --remove-bpe --lenpen 1.6 --gen-subset test --quiet

WMT16 En-De

Training and evaluating TaLK Convolutions on WMT16 En-De using cosine scheduler on one machine with 8 NVIDIA GPUs:

# Training
SAVE="checkpoints/talkconv_wmt_ende_big"
mkdir -p $SAVE

python -m torch.distributed.launch --nproc_per_node 8 fairseq-train \
    data-bin/wmt16_en_de_bpe32k --fp16 --log-interval 100 --no-progress-bar --distributed-no-spawn \
    --user-dir talkconv/talkconv_fairseq \
    --max-update 30243 --share-all-embeddings --optimizer adam \
    --adam-betas '(0.9, 0.98)' --clip-norm 0.0 --weight-decay 0.0 \
    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
    --min-lr 1e-09 --update-freq 16 \
    --ddp-backend=no_c10d --max-tokens 3584 \
    --lr-scheduler cosine --warmup-init-lr 1e-7 --warmup-updates 10000 \
    --lr-shrink 1 --max-lr 0.001 --lr 1e-7 --min-lr 1e-9 --warmup-init-lr 1e-07 \
    --t-mult 1 --lr-period-updates 20000 \
    --arch talkconv_wmt_en_de_big \
    --save-dir $SAVE

# Checkpoint averaging
python utilss/average_checkpoints.py --inputs $SAVE \
    --num-epoch-checkpoints 10 --output "${SAVE}/model.pt"

# Evaluation on newstest2014
CUDA_VISIBLE_DEVICES=0 \
fairseq-generate data-bin/wmt16_en_de_bpe32k --user-dir talkconv/talkconv_fairseq \
  --path "${SAVE}/model.pt" \
  --batch-size 128 --beam 4 --remove-bpe --lenpen 0.35 --gen-subset test > wmt14_gen_ende.txt 

bash utils/compound_split_bleu.sh wmt14_gen_ende.txt

WMT14 En-Fr

Training and evaluating TaLK Convolutions on WMT14 En-Fr using cosine scheduler on one machine with 8 NVIDIA GPUs:

# Training
SAVE="checkpoints/talkconv_wmt_enfr_big"
mkdir -p $SAVE
python -m torch.distributed.launch --nproc_per_node 8 fairseq-train \
    data-bin/wmt14_en_fr --fp16 --log-interval 100 --no-progress-bar --distributed-no-spawn \
    --user-dir talkconv/talkconv_fairseq \
    --max-update 80000 --share-all-embeddings --optimizer adam \
    --adam-betas '(0.9, 0.98)' --clip-norm 0.0 --weight-decay 0.0 \
    --criterion label_smoothed_cross_entropy --label-smoothing 0.1 \
    --min-lr 1e-09 --update-freq 32 \
    --ddp-backend=no_c10d --max-tokens 1800 \
    --lr-scheduler cosine --warmup-init-lr 1e-7 --warmup-updates 10000 \
    --lr-shrink 1 --max-lr 0.001 --lr 1e-7 --min-lr 1e-9 --warmup-init-lr 1e-07 \
    --t-mult 1 --lr-period-updates 70000 \
    --arch talkconv_wmt_en_fr_big \
    --save-dir $SAVE

# Checkpoint averaging
python utils/average_checkpoints.py --inputs $SAVE \
    --num-epoch-checkpoints 10 --output "${SAVE}/model.pt"

# Evaluation
CUDA_VISIBLE_DEVICES=0 \
fairseq-generate data-bin/wmt14_en_fr --user-dir talkconv/talkconv_fairseq \
    --path "${SAVE}/model.pt" \
    --batch-size 128 --beam 6 --remove-bpe --lenpen 0.65 --gen-subset test --quiet

License

This project is MIT-licensed. The license applies to the pre-trained models as well.

Official PyTorch implementation of Time-aware Large Kernel (TaLK) Convolutions (ICML 2020)

Related tags

Overview

Time-aware Large Kernel (TaLK) Convolutions (Lioutas et al., 2020)

Video Presentation:

Citation:

Setup

Requirements

Clone this repository

Efficient CUDA Kernels

Translation

Pre-trained models

Preprocessing the training datasets

IWSLT14 De-En

WMT16 En-De

WMT14 En-Fr

License

Owner

Vasileios Lioutas

Python package for Turkish Language.

An open collection of annotated voices in Japanese language

simpleT5 is built on top of PyTorch-lightning⚡️ and Transformers🤗 that lets you quickly train your T5 models.

A simple word search made in python

pysentimiento: A Python toolkit for Sentiment Analysis and Social NLP tasks

neural network based speaker embedder

Code for producing Japanese GPT-2 provided by rinna Co., Ltd.

The repository for the paper: Multilingual Translation via Grafting Pre-trained Language Models

Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

SGMC: Spectral Graph Matrix Completion

Malware-Related Sentence Classification

Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers

TaCL: Improve BERT Pre-training with Token-aware Contrastive Learning

Sentiment Classification using WSD, Maximum Entropy & Naive Bayes Classifiers

Asr abc - Automatic speech recognition(ASR),中文语音识别

PhoNLP: A BERT-based multi-task learning toolkit for part-of-speech tagging, named entity recognition and dependency parsing

This repository serves as a place to document a toy attempt on how to create a generative text model in Catalan, based on GPT-2

PyTorch implementation of NATSpeech: A Non-Autoregressive Text-to-Speech Framework

Seq2seq attn - Use the Seq2Seq method to implement machine translation and introduce Attention mechanism to improve the results

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