Light

slientge / sequential_recommendation_tensorflow Goto Github PK

View Code? Open in Web Editor NEW

114.0 2.0 24.0 867 KB

Several sequential recommended models implemented by tenosrflow1.x

Python 100.00%

recommendation tensorflow python caser gru4rec attrec fpmc transrec sequential-recommendation sasrec

sequential_recommendation_tensorflow's Introduction

Sequential_Recommendation_Tensorflow

In this repository, a number of sequential recommendation models are implemented using Python and Tensorflow. The implemented models cover common sequential recommendation algorithms (session based ). We implement the code in the paper in a concise way, including how to construct samples and training, to help readers better understand the paper's ideas.

Algorithms Implemented

So far, we have implemented these models, covering deep learning and traditional methods. Follow up to continue to update。

model	paper	methods
AttRec	Next Item Recommendation with Self-Attention	self-attention
Caser	Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding	CNN
GRU4Rec	Session-based Recommendations with Recurrent Neural Networks	GRU
FPMC	Factorizing Personalized Markov Chains for Next-Basket Recommendation	MF+MC
TransRec	Translation-based Recommendation	MF
SASRec	Self-Attentive Sequential Recommendation	transfomer

and so on.

Usage

To use the code, enter the models directory and execute run_Model.py such as:

cd models/AttRec
python run_Attrec.py

Note: Due to the different sample construction methods and experimental methods of different algorithms, we generate independent codes for each algorithm.

Requirements

Tensorflow 1.1+
Python 3.6+,
numpy
pandas

ToDo List

More models
Code refactoring
Support tf.data.datasets and tf.estimator

sequential_recommendation_tensorflow's People

Contributors

Stargazers

Watchers

sequential_recommendation_tensorflow's Issues

from model_SASRec import SASRec

Wish the author to complete SASRec model, please. I guess there is a missing file called model_SASRec.py.

make_datasets.py line 23

Should not it be all_user_count = len(user_map) ? Instead of item_map?

Upgrade to TensorFlow 2.0

Got a lot of errors running your code. Could you please upgrade your code to use TF 2.0?

other dataset

I have tried to test the AttRec model with other datasets, but have been unsuccessful. Excuse me, what are the requirements for the dataset?

Little typo about make_datasets.py

# ReMap usr ids
user_unique = data['user'].unique().tolist()
user_map = dict(zip(user_unique, range(1, len(user_unique) + 1)))
user_map[-1] = 0
all_user_count = len(**_user_map_**)
data['user'] = data['user'].apply(lambda x: user_map[x])

SEQNBT code

Are you planing to add the code for SEQNBT from: https://arxiv.org/pdf/2207.06225v1.pdf ?

About FPMC

fmc = torch.mean(fmc, dim=-1)是否需要修改为

fmc = torch.div(torch.sum(torch.matmul(Vil, Vli.permute(0, 2, 1)), dim=-1), item_list_len.float())
item_list_seq与pred的score是否应该除以其实际的长度而不是tf.mean

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.