RecBole 2.0: Towards a More Up-to-Date Recommendation Library

TL;DR

RecBole 2.0 is an expanded recommendation library that includes new packages addressing recent challenges like data sparsity, bias, and distribution shift, with unified implementations for advanced models.

Contribution

The paper introduces eight new packages for RecBole, covering recent topics and architectures, with comprehensive implementations to support up-to-date recommender system research.

Findings

Includes 65 new models across packages.

Provides unified framework for data and model evaluation.

Facilitates research on recent recommender system challenges.

Abstract

In order to support the study of recent advances in recommender systems, this paper presents an extended recommendation library consisting of eight packages for up-to-date topics and architectures. First of all, from a data perspective, we consider three important topics related to data issues (i.e., sparsity, bias and distribution shift), and develop five packages accordingly: meta-learning, data augmentation, debiasing, fairness and cross-domain recommendation. Furthermore, from a model perspective, we develop two benchmarking packages for Transformer-based and graph neural network (GNN)-based models, respectively. All the packages (consisting of 65 new models) are developed based on a popular recommendation framework RecBole, ensuring that both the implementation and interface are unified. For each package, we provide complete implementations from data loading, experimental setup, evaluation and algorithm implementation. This library provides a valuable resource to facilitate the up-to-date research in recommender systems. The project is released at the link: https://github.com/RUCAIBox/RecBole2.0.