Need help with neural-collaborative-filtering?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

yihong-chen
312 Stars 111 Forks 23 Commits 4 Opened issues

Description

pytorch version of neural collaborative filtering

Services available

!
?

Need anything else?

Contributors list

# 159,968
Python
Jupyter...
matrix-...
recomme...
10 commits
# 112,248
Python
Jupyter...
pytorch
recomme...
2 commits

neural-collaborative-filtering

Neural collaborative filtering(NCF), is a deep learning based framework for making recommendations. The key idea is to learn the user-item interaction using neural networks. Check the follwing paper for details about NCF.

He, Xiangnan, et al. "Neural collaborative filtering." Proceedings of the 26th International Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 2017.

The authors of NCF actually published a nice implementation written in tensorflow(keras). This repo instead provides my implementation written in pytorch. I hope it would be helpful to pytorch fans. Have fun playing with it !

Dataset

The Movielens 1M Dataset is used to test the repo.

Files

data.py
: prepare train/test dataset

utils.py
: some handy functions for model training etc.

metrics.py
: evaluation metrics including hit ratio(HR) and NDCG

gmf.py
: generalized matrix factorization model

mlp.py
: multi-layer perceptron model

neumf.py
: fusion of gmf and mlp

engine.py
: training engine

train.py
: entry point for train a NCF model

Performance

The hyper params are not tuned. Better performance can be achieved with careful tuning, especially for the MLP model. Pretraining the user embedding & item embedding might be helpful to improve the performance of the MLP model.

Experiments' results with

num_negative_samples = 4
and
dim_latent_factor=8
are shown as follows

GMF V.S. MLP

Note that the MLP model was trained from scratch but the authors suggest that the performance might be boosted by pretrain the embedding layer with GMF model.

NeuMF pretrain V.S no pretrain

The pretrained version converges much faster.

L2 regularization for GMF model

Large l2 regularization might lead to the bug of

HR=0.0 NDCG=0.0

L2 regularization for MLP model

a bit l2 regulzrization seems to improve the performance of the MLP model

L2 for MLP

MLP with pretrained user/item embedding

Pre-training the MLP model with user/item embedding from the trained GMF gives better result.

MLP network size = [16, 64, 32, 16, 8]

Pretrain for MLP Pretrain for MLP

Implicit feedback without pretrain

Ratings are set to 1 (interacted) or 0 (uninteracted). Train from scratch. binarize

Pytorch Versions

The repo works under torch 1.0. You can find the old versions working under torch 0.2 and 0.4 in tags.

TODO

  • Batchify the test data to handle large dataset.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.