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.

A pytorch implementation for BPR (Bayesian Personalized Ranking).

Bayesian Personalized Ranking using PyTorch

DEPRECATED This is the official repository for the 2017 Recommender Systems course at Polimi.

矩阵分解(BPRMF) + 知识图谱表示学习(TransR) 构建的推荐系统

Repository for PAI-BPR a state of the art Fashion recommendation system capturing user personal preference and attribute interpretability

BPR recommender system

Predicting missing pairwise preferences from similarity features in group decision making and group recommendation system

Bayesian Personalized Ranking in Python

PyTorch implementations of collaborative filtering methods with implicit feedback

Set of recommender systems

A personality-aware group recommendation system based on pairwise preferences

Comparing Exploitation-Based and Game Theory Optimal Based Approaches in a Multi-Agent Environment (2020 Spring)

Set of music recommendation algorithms we implemented to join the annual RecSys Competition at Politecnico di Milano in 2017.

BPR-Based Recommender Systems for Amazon Dataset

基于 pytorch 复现了 Causal Intervention for Leveraging Popularity Bias in Recommendation 中的提到的 Popularity-bias Deconfounding (PD) 和 Popularity-bias Deconfounding and Adjusting (PDA) 方法

支持快速实现基于多元隐式反馈的BPR变体算法开源库

Bayesian Personalized Ranking is a learning algorithm for collaborative filtering first introduced in: BPR: Bayesian Personalized Ranking from Implicit Feedback. Steffen Rendle, Christoph Freudenthaler, Zeno Gantner and Lars Schmidt-Thieme, Proc. UAI 2009.

Unofficial Implementation of BPRH: Bayesian personalized ranking for heterogeneous implicit feedback