RecBole has included more than 50 widely used recommendation algorithms.

Model list

In the first version, we implement RecBole recommendation models covering general recommendation, sequential recommendation, context-aware recommendation and knowledge-based recommendation. We summarize the models in the following table:

Category Model Conference Year Paper
General recommendation
popularity - - -
ItemKNN TOIS 2004 《Item-based top-N recommendation algorithms》
BPR UAI 2009 《BPR: Bayesian Personalized Ranking from Implicit Feedback》
NeuMF WWW 2017 《Neural Collaborative Filtering》
ConvNCF IJCAI 2017 《Outer Product-based Neural Collaborative Filtering》
DMF IJCAI 2017 《Deep Matrix Factorization Models for Recommender Systems》
FISM SIGKDD 2013 《FISM: Factored Item Similarity Models for Top-N Recommender Systems》
NAIS TKDE 2018 《NAIS: Neural Attentive Item Similarity Model for Recommendation》
SpectralCF RecSys 2018 《Spectral Collaborative Filtering》
GCMC SIGKDD 2018 《Graph Convolutional Matrix Completion》
NGCF SIGIR 2019 《Neural Graph Collaborative Filtering》
LightGCN SIGIR 2020 《LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation》
DGCF SIGIR 2020 《Disentangled Graph Collaborative Filtering》
MultiVAE WWW 2018 《Variational Autoencoders for Collaborative Filtering》
MultiDAE WWW 2018 《Variational Autoencoders for Collaborative Filtering》
CDAE WSDM 2016 《Collaborative denoising auto-encoders for top-n recommender systems》
MacridVAE NeurIPS 2019 《Learning Disentangled Representations for Recommendation》
LINE WWW 2015 《Large-scale Information Network Embedding》
Context-aware recommendation
LR WWW 2007 《Predicting Clicks Estimating the Click-Through Rate for New Ads》
FM ICDM 2010 《Factorization Machines》
NFM SIGIR 2017 《Neural Factorization Machines for Sparse Predictive Analytics》
DeepFM IJCAI 2017 《DeepFM A Factorization-Machine based Neural Network for CTR Prediction》
xDeepFM SIGKDD 2018 《xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems》
AFM IJCAI 2017 《Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks》
FFM RecSys 2016 《Field-aware Factorization Machines for CTR Prediction》
FwFM WWW 2018 《Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising》
FNN(DNN) ECIR 2016 《Deep Learning over Multi-field Categorical Data》
PNN ICDM 2016 《Product-based Neural Networks for User Response Prediction》
DSSM CIKM 2013 《Learning Deep Structured Semantic Models for Web Search using Clickthrough Data》
Wide&Deep RecSys 2016 《Wide & Deep Learning for Recommender Systems》
DIN SIGKDD 2018 《Deep Interest Network for Click-Through Rate Prediction》
DCN ADKDD 2017 《Deep & Cross Network for Ad Click Predictions》
AutoInt CIKM 2019 《AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks》
XGBoost KDD 2016 《XGBoost: A Scalable Tree Boosting System》
Sequential recommendation
FPMC WWW 2010 《Factorizing Personalized Markov Chains for Next-Basket Recommendation》
Improved GRU-Rec DLRS 2016 《Improved recurrent neural networks for session-based recommendations》
NARM CIKM 2017 《Neural attentive session-based recommendation》
STAMP SIGKDD 2018 《STAMP: short-term attention/memory priority model for session-based recommendation.》
Caser WSDM 2018 《Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding》
NextItnet WSDM 2019 《A simple convolutional generative network for next item recommendation》
TransRec RecSys 2017 《Translation-based Recommendation》
SASRec ICDM 2018 《Self-Attentive Sequential Recommendation》
BERT4Rec CIKM 2019 《BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer》
SRGNN AAAI 2019 《Session-Based Recommendation with Graph Neural Networks》
GCSAN IJCAI 2019 《Graph contextualized self-attention network for session-based recommendation》
GRU4RecF(+feature embedding) RecSys 2016 《Parallel Recurrent Neural Network Architectures for Feature-rich Session-based Recommendations》
SASRecF(+feature embedding) IJCAI 2019 《Feature-level Deeper Self-Attention Network for Sequential Recommendation》
FDSA IJCAI 2019 《Feature-level Deeper Self-Attention Network for Sequential Recommendation》
S3Rec CIKM 2020 《S^3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization》
GRU+KG Embedding - - -
KSR SIGIR 2018 《Improving Sequential Recommendation with Knowledge-Enhanced Memory Networks》
Fossil ICDM 2016 《Fusing similarity models with Markov chains for sparse sequential recommendation》
RepeatNet AAAI 2019 《A Repeat Aware Neural Recommendation Machine for Session-based Recommendation》
SHAN IJCAI 2018 《Sequential Recommender System based on Hierarchical Attention Network》
NPE IJCAI 2018 《Neural Personalized Embedding for Collaborative Filtering》
HRM SIGIR 2015 《Learning Hierarchical Representation Model for Next Basket Recommendation》
HGN SIGKDD 2019 《Hierarchical Gating Networks for Sequential Recommendation》
Knowledge-based recommendation
CKE SIGKDD 2016 《Collaborative Knowledge Base Embedding for Recommender Systems》
CFKG MDPI 2018 《Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation》
KTUP WWW 2019 《Unifying Knowledge Graph Learning and Recommendation:Towards a Better Understanding of User Preferences》
KGAT SIGKDD 2019 《KGAT Knowledge Graph Attention Network for Recommendation》
RippleNet CIKM 2018 《RippleNet Propagating User Preferences on the Knowledge Graph for Recommender Systems.》
MKR WWW 2019 《Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation》
KGCN WWW 2019 《Knowledge graph convolution networks for recommender systems》
KGNN-LS SIGKDD 2019 《Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems》

NOTE: For some recommendation algorithms, we cannot find the original implementation, and we implemented them according to our understanding of the original paper. Besides, parameter tuning or learning algorithm may not be the optimal way as originally expected. If this case was found, please contact us to help improve the algorithm implementation.

Time and memory costs

We constructed preliminary experiments to test the time and memory cost on three different-sized datasets (small, medium and large). For detailed information, you can click the following links.

NOTE: Our test results only gave the approximate time and memory cost of our implementations in the RecBole library (based on our machine server). Any feedback or suggestions about the implementations and test are welcome. We will keep improving our implementations, and update these test results.