guoyang9/BPR-pytorch guoyang9/BPR-pytorch

  • Stars
    star
    135
  • Rank 269,297 (Top 6 %)
  • Language
    Python
  • Created over 5 years ago
  • Updated over 5 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
guoyang9/BPR-pytorch
github

guoyang9

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A pytorch implementation for BPR (Bayesian Personalized Ranking).

Pytorch-BPR

Note that I use the two sub datasets provided by Xiangnan's repo. Another pytorch NCF implementaion can be found at this repo.

I utilized a factor number 32, and posted the results in the NCF paper and this implementation here. Since there is no specific numbers in their paper, I found this implementation achieved a better performance than the original curve. Moreover, the batch_size is not very sensitive with the final model performance.

Models MovieLens HR@10 MovieLens NDCG@10 Pinterest HR@10 Pinterest NDCG@10
pytorch-BPR 0.700 0.418 0.877 0.551

The requirements are as follows:

* python==3.6
* pandas==0.24.2
* numpy==1.16.2
* pytorch==1.0.1
* tensorboardX==1.6 (mainly useful when you want to visulize the loss, see https://github.com/lanpa/tensorboard-pytorch)

Example to run:

python main.py --factor_num=16 --lamda=0.001

More Repositories

1

NCF

A pytorch implementation of He et al. "Neural Collaborative Filtering" at WWW'17
Python
337
star
2

NFM-pyorch

A pytorch implementation for He et al. Neural Factorization Machines for Sparse Predictive Analytics on SIGIR 2017.
Python
39
star
3

A3NCF

Implementation for Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews.
Python
25
star
4

ALSTP

Implementation for our TOIS paper --- Attentive Long Short-Term Preference Modeling for Personalized Product Search.
Python
17
star
5

UnifER

Official implementation for the MM'22 paper.
Python
11
star
6

PELA

PELA: Learning Parameter-Efficient Models with Low-Rank Approximation [CVPR 2024]
Python
10
star
7

TranSearch

Implementation for our MM'18 paper --- Multi-modal Preference Modeling for Product Search.
Python
9
star
8

LXMERT-VQACP

This is an adaptation of LXMERT on both VQA-CP and VQA dataset.
Python
6
star
9

AdaVQA

Implementation for our IJCAI-21 paper --- AdaVQA: Overcoming Language Priors with Adapted Margin Loss.
Python
6
star
10

Relation-Fact-Detector

The Relation Fact Detector in 'R-VQA: Learning Visual Relation Facts with Semantic Attention for Visual Question Answering'.
Python
6
star
11

vqa-prior

Implementation for our SIGIR 2019 paper --- Quantifying and Alleviating the Language Prior Problem in Visual Question Answering.
Python
6
star
12

class-imbalance-VQA

Implementation for our TIP paper - Loss Re-scaling VQA: Revisiting the Language Prior Problem from a Class-imbalance View.
Python
5
star
13

ELIP

Efficient language image pre-training
Python
2
star
14

CF-PPS

Personalized product search with collaborative filtering and some typical baselines.
Python
1
star
15

UNK-VQA

A VQA dataset that includes unanswerable questions [TPAMI 2024].
1
star