Summary of the Recommendation Algorithms¶
Elliot integrates, to date, 50 recommendation models partitioned into two sets. The first set includes 38 popular models implemented in at least two of frameworks reviewed in this work (i.e., adopting a framework-wise popularity notion).
All the recommendation models inherit from a common abstract class:
The majority of the recommendation models uses a Mixin:
Adversarial Learning
|
Adversarial Matrix Factorization |
|
Adversarial Multimedia Recommender |
Algebric
Slope One Predictors for Online Rating-Based Collaborative Filtering |
Autoencoders
|
Collaborative denoising autoencoder |
|
Variational Autoencoders for Collaborative Filtering |
Content-Based
Vector Space Model |
Generative Adversarial Networks (GANs)
|
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models |
|
CFGAN: A Generic Collaborative Filtering Framework based on Generative Adversarial Networks |
Graph-based
LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation |
|
|
Neural Graph Collaborative Filtering |
Knowledge-aware
|
Knowledge-aware Hybrid Factorization Machines |
Knowledge-aware Hybrid Factorization Machines (Tensorflow Batch Variant) |
|
|
Knowledge-aware Hybrid Factorization Machines (Tensorflow Embedding-based Variant) |
Latent Factor Models
Bayesian Personalized Ranking with Matrix Factorization |
|
Batch Bayesian Personalized Ranking with Matrix Factorization |
|
BPR Sparse Linear Methods |
|
|
Collaborative Metric Learning |
|
Field-aware Factorization Machines |
|
FISM: Factored Item Similarity Models |
Factorization Machines |
|
For further details, please refer to the paper |
|
|
Logistic Matrix Factorization |
Matrix Factorization |
|
|
Non-Negative Matrix Factorization |
|
Probabilistic Matrix Factorization |
For further details, please refer to the paper |
|
|
Train a Sparse Linear Methods (SLIM) item similarity model. |
SVD++ |
|
|
Weighted XXX Matrix Factorization |
Artificial Neural Networks
Convolutional Matrix Factorization for Document Context-Aware Recommendation |
|
|
Outer Product-based Neural Collaborative Filtering |
|
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction |
Deep Matrix Factorization Models for Recommender Systems. |
|
|
Neural Collaborative Filtering |
AutoRec: Autoencoders Meet Collaborative Filtering (Item-based) |
|
|
NAIS: Neural Attentive Item Similarity Model for Recommendation |
Neural Collaborative Filtering |
|
|
Neural Factorization Machines for Sparse Predictive Analytics |
Neural Personalized Ranking for Image Recommendation (Model without visual features) |
|
AutoRec: Autoencoders Meet Collaborative Filtering (User-based) |
|
Wide & Deep Learning for Recommender Systems |
Neighborhood-based Models
|
Amazon.com recommendations: item-to-item collaborative filtering |
|
GroupLens: An Open Architecture for Collaborative Filtering of Netnews |
|
Attribute Item-kNN proposed in MyMediaLite Recommender System Library |
|
Attribute User-kNN proposed in MyMediaLite Recommender System Library |
Unpersonalized Recommenders
Visual Models
|
Attentive Collaborative Filtering: Multimedia Recommendation with Item- and Component-Level Attention |
DeepStyle: Learning User Preferences for Visual Recommendation |
|
Visually-Aware Fashion Recommendation and Design with Generative Image Models |
|
|
VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback |
|
Visual Neural Personalized Ranking for Image Recommendation |
|
Adversarial Multimedia Recommender |