cheungdaven / Deeprec
Licence: gpl-3.0
An Open-source Toolkit for Deep Learning based Recommendation with Tensorflow.
Stars: ✭ 954
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Deeprec
Recommendation-System-Baseline
Some common recommendation system baseline, with description and link.
Stars: ✭ 34 (-96.44%)
Mutual labels: collaborative-filtering, matrix-factorization, recommendation-system
Recsys2019 deeplearning evaluation
This is the repository of our article published in RecSys 2019 "Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches" and of several follow-up studies.
Stars: ✭ 780 (-18.24%)
Mutual labels: collaborative-filtering, matrix-factorization, recommendation-system
recommender system with Python
recommender system tutorial with Python
Stars: ✭ 106 (-88.89%)
Mutual labels: collaborative-filtering, matrix-factorization, recommendation-system
Cornac
A Comparative Framework for Multimodal Recommender Systems
Stars: ✭ 308 (-67.71%)
Mutual labels: collaborative-filtering, matrix-factorization, recommendation-system
Tf-Rec
Tf-Rec is a python💻 package for building⚒ Recommender Systems. It is built on top of Keras and Tensorflow 2 to utilize GPU Acceleration during training.
Stars: ✭ 18 (-98.11%)
Mutual labels: matrix-factorization, recommendation-system
Recommendation.jl
Building recommender systems in Julia
Stars: ✭ 42 (-95.6%)
Mutual labels: collaborative-filtering, matrix-factorization
TIFUKNN
kNN-based next-basket recommendation
Stars: ✭ 38 (-96.02%)
Mutual labels: collaborative-filtering, recommendation-system
recommender
NReco Recommender is a .NET port of Apache Mahout CF java engine (standalone, non-Hadoop version)
Stars: ✭ 35 (-96.33%)
Mutual labels: collaborative-filtering, recommendation-system
Quick-Data-Science-Experiments-2017
Quick-Data-Science-Experiments
Stars: ✭ 19 (-98.01%)
Mutual labels: collaborative-filtering, matrix-factorization
Awesome-Machine-Learning-Papers
📖Notes and remarks on Machine Learning related papers
Stars: ✭ 35 (-96.33%)
Mutual labels: collaborative-filtering, matrix-factorization
Mrsr
MRSR - Matlab Recommender Systems Research is a software framework for evaluating collaborative filtering recommender systems in Matlab.
Stars: ✭ 13 (-98.64%)
Mutual labels: collaborative-filtering, matrix-factorization
datatheque.com
a data science blog
Stars: ✭ 12 (-98.74%)
Mutual labels: collaborative-filtering, recommendation-system
Librec
LibRec: A Leading Java Library for Recommender Systems, see
Stars: ✭ 3,045 (+219.18%)
Mutual labels: collaborative-filtering, matrix-factorization
Recbole
A unified, comprehensive and efficient recommendation library
Stars: ✭ 780 (-18.24%)
Mutual labels: collaborative-filtering, recommendation-system
retailbox
🛍️RetailBox - eCommerce Recommender System using Machine Learning
Stars: ✭ 32 (-96.65%)
Mutual labels: matrix-factorization, recommendation-system
Person-Recommendation-Algorithms
推荐算法个人学习笔记以及代码实战
Stars: ✭ 50 (-94.76%)
Mutual labels: collaborative-filtering, recommendation-system
matrix-completion
Lightweight Python library for in-memory matrix completion.
Stars: ✭ 94 (-90.15%)
Mutual labels: collaborative-filtering, matrix-factorization
raptor
A lightweight product recommendation system (Item Based Collaborative Filtering) developed in Haskell.
Stars: ✭ 34 (-96.44%)
Mutual labels: collaborative-filtering, recommendation-system
Neural Collaborative Filtering
pytorch version of neural collaborative filtering
Stars: ✭ 263 (-72.43%)
Mutual labels: collaborative-filtering, matrix-factorization
Daisyrec
A developing recommender system in pytorch. Algorithm: KNN, LFM, SLIM, NeuMF, FM, DeepFM, VAE and so on, which aims to fair comparison for recommender system benchmarks
Stars: ✭ 280 (-70.65%)
Mutual labels: collaborative-filtering, matrix-factorization
DeepRec
In this repository, a number of deep learning based recommendation models are implemented using Python and Tensorflow. We started this project in the hope that it would reduce the efforts of researchers and developers in reproducing state-of-the-art methods. The implemented models cover three major recommendation scenarios: rating prediction, top-N recommendation (i.e., item ranking) and sequential recommendation. Meanwhile, DeepRec maintains good modularity and extensibility for easy incorporation of new models into this framework. DeepRec is distributed under the GNU General Public License.
Anyone who is interested in contributing to this project, please contact me!
Algorithms Implemented
We implemented both rating estimation, top-n recommendation models and sequence-aware recommendation models.
- I-AutoRec and U-AutoRec (www'15)
- CDAE (WSDM'16)
- NeuMF (WWW'17)
- CML (WWW'17)
- LRML (WWW'18) (DRAFT version)
- NFM (SIGIR'17)
- NNMF (arxiv)
- PRME (IJCAI 2015)
- CASER (WSDM 2018)
- AttRec (AAAI 2019 RecNLP) and so on.
To use the code, run: Test/test_item_ranking.py, Test/test_rating_pred.py, or Test/testSeqRec.py
Requirements
- Tensorflow 1.7+, Python 3.5+, numpy, scipy, sklearn, pandas
ToDo List
- More deep-learning based models
- Alternative evaluation protocols
- Code refactoring
- Update to Tensorflow 2.0
Citation
To acknowledge use of this open source package in publications, please cite either of the following papers:
@article{zhang2019deeprecsyscsur,
title={Deep learning based recommender system: A survey and new perspectives},
author={Zhang, Shuai and Yao, Lina and Sun, Aixin and Tay, Yi},
journal={ACM Computing Surveys (CSUR)},
volume={52},
year={2019},
publisher={ACM}
}
or
@inproceedings{shuai2019deeprec,
title={DeepRec: An Open-source Toolkit for Deep Learning based Recommendation},
author={Shuai Zhang, Yi Tay, Lina Yao, Bin Wu, Aixin Sun},
journal={arXiv preprint arXiv:1905.10536},
year={2019}
}
Thank you for your support!
The chinese version is host here.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].