---

HomePage | Docs | GitHub | Datasets | v0.1.2 | v0.2.0 | v1.0.0 | v1.0.1 | v1.1.1 | v1.2.0

Introduction

RecBole is a unified, comprehensive and efficient framework developed based on PyTorch. It aims to help the researchers to reproduce and develop recommendation models.

In the lastest release, our library includes 94 recommendation algorithms [Model List], covering four major categories:

• General Recommendation

• Sequential Recommendation

• Context-aware Recommendation

• Knowledge-based Recommendation

We design a unified and flexible data file format, and provide the support for 44 benchmark recommendation datasets [Collected Datasets]. A user can apply the provided script to process the original data copy, or simply download the processed datasets by our team.

Features:

• General and extensible data structure

  We deign general and extensible data structures to unify the formatting and usage of various recommendation datasets.

• Comprehensive benchmark models and datasets

  We implement 94 commonly used recommendation algorithms, and provide the formatted copies of 44 recommendation datasets.

• Efficient GPU-accelerated execution

  We design many tailored strategies in the GPU environment to enhance the efficiency of our library.

• Extensive and standard evaluation protocols

  We support a series of commonly used evaluation protocols or settings for testing and comparing recommendation algorithms.

Get Started

• Install RecBole
• Quick Start
• Distributed Training

User Guide

• Config Introduction
• Data Module Introduction
• Model Introduction
• Training & Evaluation Introduction
• Usage

Developer Guide

• Customize Models
• Customize Trainers
• Customize DataLoaders
• Customize Samplers
• Customize Metrics

API REFERENCE:

• recbole.config.configurator
• Config
• recbole.data
• recbole.evaluator
• recbole.model
• recbole.quick_start
• load_data_and_model()
• objective_function()
• run()
• run_recbole()
• run_recboles()
• recbole.sampler
• AbstractSampler
• KGSampler
• RepeatableSampler
• Sampler
• SeqSampler
• recbole.trainer.hyper_tuning
• ExhaustiveSearchError
• HyperTuning
• exhaustive_search()
• recbole.trainer.trainer
• AbstractTrainer
• DecisionTreeTrainer
• KGATTrainer
• KGTrainer
• LightGBMTrainer
• MKRTrainer
• NCLTrainer
• PretrainTrainer
• RaCTTrainer
• RecVAETrainer
• S3RecTrainer
• TraditionalTrainer
• Trainer
• XGBoostTrainer
• recbole.utils.case_study
• full_sort_scores()
• full_sort_topk()
• recbole.utils.enum_type
• EvaluatorType
• FeatureSource
• FeatureType
• InputType
• KGDataLoaderState
• ModelType
• recbole.utils.logger
• RemoveColorFilter
• init_logger()
• set_color()
• recbole.utils.utils
• calculate_valid_score()
• dict2str()
• early_stopping()
• ensure_dir()
• get_environment()
• get_flops()
• get_gpu_usage()
• get_local_time()
• get_model()
• get_tensorboard()
• get_trainer()
• init_seed()
• list_to_latex()

The Team

RecBole is developed and maintained by RUC, BUPT, ECNU.

Here is the list of our lead developers in each development phase. They are the souls of RecBole and have made outstanding contributions.

Time	Version	Lead Developers
June 2020 ~ Nov. 2020	v0.1.1	Shanlei Mu, Yupeng Hou, Zihan Lin, Kaiyuan Li
Nov. 2020 ~ Oct. 2022	v0.1.2 ~ v1.0.1	Yushuo Chen, Xingyu Pan
Oct. 2022 ~ Nov. 2023	v1.1.0 ~ v1.1.1	Lanling Xu, Zhen Tian, Gaowei Zhang, Lei Wang, Junjie Zhang
Nov. 2023 ~ Feb. 2025	v1.2.0	Bowen Zheng, Chen Ma
Feb. 2025 ~ Now	v1.2.1	Enze Liu, Kesha Ou, Bingqian Li

License

RecBole uses MIT License.