RecsysTutorial

추천시스템 논문을 읽고 구현한 Code가 저장된 Recsys Tutorial Repository 입니다.

논문 리뷰가 저장된 벨로그 주소: https://velog.io/@2712qwer/series/RecSys-Paper

Used Data

• MovieLens - 100k
• Criteo CTR DataSet - 1GB

Implementation List

Session-based

• ItemSage

  • (2022). ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterest

• PinnerForme

  • (2022). PinnerFormer: Sequence Modeling for User Representation at Pinterest

• S3-Rec

  • (2020). S3-Rec: Self-Supervised Learning for Sequential Recommendation with Mutual Information Maximization

• BERT4Rec - MovieLens

  • (2019). BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer

• SASRec - MovieLens

  • (2018). Self-Attentive Sequential Recommendation

• Caser - MovieLens

  • (2018). Personalized Top-N Sequential Recommendation Via Convolutional Sequence Embedding

• GRU4Rec

  • (2016). Session-based Recommendations with Recurrent Neural Networks

GNN-based

• SGCF

  • (2023). Simplifying Graph-based Collaborative Filtering for Recommendation

• SimGCL

  • (2021). Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation

• LightGCN - MovieLens

  • (2020). LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation

• MultiSAGE - MovieLens

  • (2020). MultiSage: Empowering GCN with Contextualized Multi-Embeddings on Web-Scale Multipartite Networks

• SIGN

  • (2020). SIGN: Scalable Inception Graph Neural Networks

• FastGCN

  • (2019). Simplifying Graph Convolutional Networks

• NGCF - MovieLens

  • (2019). Neural Graph Collaborative Filtering

• PinSage - MovieLens

  • (2018). Graph Convolutional Neural Networks for Web-Scale Recommender Systems

• SR-GNN

  • (2018). Session-based Recommendation with Graph Neural Networks

• GraphSAGE - MovieLens

  • (2017). Inductive Representation Learning on Large Graphs

• GC-MC

  • (2017). Graph Convolutional Matrix Completion

• Pixie - MovieLens

  • (2017). Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time

• GAT

  • (2017). Graph Attention Networks

• GCN

  • (2016). Semi-Supervised Classification with Graph Convolutional Networks

• DeepWalk - MovieLens

  • (2014). DeepWalk: Online Learning of Social Representations

AutoEncoder-based

• EASER - MovieLens

  • (2021). Negative Interactions for Improved Collaborative Filtering: Don’t go Deeper, go Higher

• ADMM SLIM - MovieLens

  • (2020). ADMM SLIM: Sparse Recommendations for Many Users

• RecVAE - MovieLens

  • (2019). RecVAE: a New Variational Autoencoder for Top-N Recommendations with Implicit Feedback

• EASE - MovieLens

  • (2019). Embarrassingly Shallow Autoencoders for Sparse Data

• Multi-VAE & Multi-DAE - MovieLens

  • (2018). Variational Autoencoders for Collaborative Filtering

• CDAE - MovieLens

  • (2016). Collaborative Denoising Auto-Encoders for Top-N Recommender Systems

• AutoRec - MovieLens

  • (2015). Autorec: Autoencoders Meet Collaborative Filtering

이외

• PinnerSage

  • (2020). PinnerSage: Multi-Modal User Embedding Framework for Recommendations at Pinterest

• Time2Vec

  • (2019). Time2Vec: Learning a Vector Representation of Time

• NCF - MovieLens

  • (2017). Neural Collaborative Filtering

• DeepFM - CTR

  • (2017). DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

• Item2Vec - MovieLens

  • (2016). Item2Vec : Neural Item Embedding for Collaborative Filtering

• FM - CTR

  • (2010). Factorization Machines

• BPR - MovieLens

  • (2009). BPR: Bayesian Personalized Ranking from Implicit Feedback

• MF - MovieLens

  • (2009). Matrix Factorization Techniques for Recommender Systems