Light

ustcml / lisa Goto Github PK

View Code? Open in Web Editor NEW

0.0 0.0 0.0 9.42 MB

Pytorch implementation of LISA (Linear-Time Self Attention with Codeword Histogram for Efficient Recommendation. WWW 2021)

Python 100.00%

efficient-transformers product-quantization self-attention efficient-recommendation

lisa's Introduction

Requirements

PyTorch 1.6.0
numpy
tqdm

Usage

train_efficient_attention_target_seperate_pq.py, train_efficient_attention_soft_pq.py, train_efficient_attention.py correspond to the LISA-Mini, LISA-Soft, LISA-Base models, respectively.

train_transformer.py corresponds to the vanilla Transformer based model.

To train LISA-Mini on ML-1M dataset, run:

python train_efficient_attention_target_seperate_pq.py --config configs/EfficientAttn-Mini/ml-1m-256.json --train_dataset datasets/ml-1m/train.pkl --eval_dataset datasets/ml-1m/eval.pkl --gpu 0

To train LISA-Soft, run:

python train_efficient_attention_soft_pq.py --config configs/EfficientAttn-Soft/ml-1m-128.json --train_dataset datasets/ml-1m/train.pkl --eval_dataset datasets/ml-1m/eval.pkl --gpu 0

To train LISA-Base, run:

python train_efficient_attention.py --config configs/EfficientAttn-Base/ml-1m.json --train_dataset datasets/ml-1m/train.pkl --eval_dataset datasets/ml-1m/eval.pkl --gpu 0

To train the vanilla Transformer, run:

python train_transformer.py --config configs/Transformer/ml-1m.json --train_dataset datasets/ml-1m/train.pkl --eval_dataset datasets/ml-1m/eval.pkl --gpu 0

lisa's People

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.