Papers on Recommendation Systems

Survey

surveys on recommendation system and computational advertising system

• Deep Learning based Recommender System A Survey and New Perspectives

Embedding

• Sequence Embedding
  • Word2Vec
  • Item2Vec
  • Listing Embedding
• DNN-based Embedding
  • AutoEncoder
  • WDL-ID2Vec
  • NCF-CF2Vec
  • YouTube DNN (Softmax Embedding)
• Graph Embedding
  • Node2Vec
  • LINE
  • DeepWalk
  • EGES

Model	Conference	Paper
Word2Vec	arxiv'13	Efficient Estimation of Word Representations in Vector Space; Distributed Representations of Words and Phrases and their Compositionality [Google]
Item2Vec	arxiv'16	Item2Vec: Neural Item Embedding for Collaborative Filtering [Microsoft]
GraphEmb	KDD'14	DeepWalk- Online Learning of Social Representations
LINE	WWW'15	LINE - Large-scale Information Network Embedding [Microsoft]
Node2Vec	KDD'16	node2vec: Scalable Feature Learning for Networks
Youtube DNN	RecSys'16	Deep Neural Networks for YouTube Recommendations [Google]
NCF	WWW'17	Neural Collaborative Filtering
Listing emb	KDD'18	Real-time Personalization using Embeddings for Search Ranking at Airbnb [Airbnb]
	KDD'18	Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba [Alibaba]
Product emb	arxiv'19	Large-scale Collaborative Filtering with Product Embeddings [Amazon]
DeepCF	AAAI'19	DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System

word2vec解释

• Word2vec Explained Negative-Sampling Word-Embedding Method (2014)
• Word2vec Parameter Learning Explained (2016)

CTR Prediction

various CTR prediction models for recommendation systems

• Tree-based series
  • GBDT+LR
• FTRL series
  • FTRL
• FM series
  • FM/FFM
• Deep series

Model	Conference	Paper
LR	WWW'07	Predicting Clicks: Estimating the Click-Through Rate for New Ads [Microsoft]
FM	ICDM'10	Factorization Machines
FTRL	KDD'13	Ad Click Prediction: a View from the Trenches [Google]
GBDT+LR	ADKDD'14	Practical Lessons from Predicting Clicks on Ads at Facebook [Facebook]
CCPM	CIKM'15	A Convolutional Click Prediction Model
FFM	RecSys'16	Field-aware Factorization Machines for CTR Prediction [Criteo]
WDL	DLRS'16	Wide & Deep Learning for Recommender Systems [Google]
FNN	ECIR'16	Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction [RayCloud]
PNN	ICDM'16	Product-based Neural Networks for User Response Prediction
Youtube DNN	RecSys'16	Deep Neural Networks for YouTube Recommendations [Google]
DeepFM	IJCAI'17	DeepFM: A Factorization-Machine based Neural Network for CTR Prediction, [Huawei]
NFM	SIGIR'17	Neural Factorization Machines for Sparse Predictive Analytics
AFM	IJCAI'17	Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks
DCN	ADKDD'17	Deep & Cross Network for Ad Click Predictions [Google]
xDeepFM	KDD'18	xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems [Microsoft]
DIN	KDD'18	Deep Interest Network for Click-Through Rate Prediction [Alibaba]
FwFM	WWW'18	Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising [LinkedIn, Ablibaba]
FPE	RecSys'18	Field-aware Probabilistic Embedding Neural Network for CTR Prediction
AutoInt	arxiv'18	AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
SASRec	ICDM'18	Self-Attentive Sequential Recommendation
IFM	AAAI'19	Interaction-aware Factorization Machines for Recommender Systems [Tencent]
DeepGBM	KDD'19	DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks [Microsoft]
OENN	SIGIR'19	Order-aware Embedding Neural Network for CTR Prediction [Huawei]
DIEN	AAAI'19	Deep Interest Evolution Network for Click Through Rate Prediction [Alibaba]
DSIN	arxiv'19	Deep Session Interest Network for Click-Through Rate Prediction [Alibaba]
OANN	arxiv'19	Operation-aware Neural Networks for User Response Prediction
FGCNN	arxiv'19	Feature Generation by Convolutional Neural Network [Huawei]
FiBiNET	RecSys'19	FiBiNET: combining feature importance and bilinear feature interaction for click-through rate prediction [Sina]

CTR预估深度模型演化之路：https://mp.weixin.qq.com/s/jpWS9ec0MCO4ncSZx38r3w https://zhuanlan.zhihu.com/p/86181485

DeepCTR：易用可扩展的深度学习点击率预测算法包： https://zhuanlan.zhihu.com/p/53231955

TL related

Transfer Learning related/Multi-Task Learning based Recommendation Systems

• An Overview of Multi-Task Learning in Deep Neural Networks
• A Survey on Transfer Learning

Model	Conference	Paper
ESMM	SIGIR’18	Entire Space Multi-Task Model: An Effective Approach for Estimating Post-Click Conversion Rate [Alibaba]
MMoE	KDD’18	Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts [Google]
YouTube-MTL	RecSys’19	Recommending What Video to Watch Next: A Multitask Ranking System [Google]
DeepMCP	IJCAI’19	Representation Learning-Assisted Click-Through Rate Prediction [Alibaba]

• Schick, Timo, and Hinrich Schütze. "It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners." arXiv preprint [arXiv:2009.07118] (2020).
• Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking, Giovanni Campagna Agata Foryciarz Mehrad Moradshahi Monica S. Lam, ACL 2020 [arXiv]
• DReCa: A General Task Augmentation Strategy for Few-Shot Natural Language Inference Shikhar Murty, Tatsunori B. Hashimoto, Christopher D. Manning, 2020 [arXiv]

FL related

Federated Learning based Recommendation Systems

• Federated Recommendation Systems

• FedFast: Going Beyond Average for Faster Training of Federated Recommender Systems

DRL related

• Deep Reinforcement Learning based Recommendation Systems

Conference	Paper
WWW'18	DRN：A Deep Reinforcement Learning Framework for News Recommendation [MSRA]
RecSys'18	Deep Reinforcement Learning for Page-wise Recommendations [JD]
Arxiv'17	Deep Reinforcement Learning for List-wise Recommendations [JD]
KDD'18	Stabilizing Reinforcement Learning in Dynamic Environment with Application to Online Recommendation
KDD'18	Reinforcement Learning to Rank in E-Commerce Search Engine: Formalization, Analysis, and Application
	https://tech.meituan.com/2018/11/15/reinforcement-learning-in-mt-recommend-system.html [Meituan]

XAI

Explainable AI and model interpretation methods for ML models

• PDP：A simple and effective model-based variable importance measure. Greenwell, Brandon M., Bradley C. Boehmke, and Andrew J. McCarthy. arXiv preprint arXiv:1805.04755 (2018).
• ICE：Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. Goldstein, Alex, Adam Kapelner, Justin Bleich, and Emil Pitkin. Journal of Computational and Graphical Statistics 24, no. 1 (2015): 44-65.
• LIME：LIME: "Why Should I Trust You?": Explaining the Predictions of Any Classifier Ribeiro, Sameer Singh, Guestrin, KDD 2016 [arXiv]
• SHAP：SHAP: A Unified Approach to Interpreting Model Predictions, Lundberg, Lee, NIPS 2017 [arXiv]
• DeepLift：DeepLift: Learning Important Features Through Propagating Activation Differences Avanti Shrikumar et al, ICML 2019 [arXiv]
• RETAIN
• LRP

Methods

• https://christophm.github.io/interpretable-ml-book/
• Principles and Practice of Explainable Machine Learning Vaishak Belle, Ioannis Papantonis [arXiv]
• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI, Arrieta et al., 2019 [arXiv]
• Definitions, methods, and applications in interpretable machine learning W. James Murdocha, Chandan Singhb, Karl Kumbiera, Reza Abbasi-Asl, and Bin Yua, PNAS 2019 [PNAS]
• How Can I Explain This to You? An Empirical Study of Deep Neural Network Explanation Methods Jeya Vikranth Jeyakumar, Joseph Noor, Yu-Hsi Cheng, Luis Garcia, Mani Srivastava, NIPS 2020 [arXiv]
• Towards Transparent and Explainable Attention Models Mohankumar, Mitesh Khapra et al. ACL 2020 [arXiv]
• A Framework for Understanding Unintended Consequences of Machine Learning Harini Suresh, John V. Guttag, 2020 [arXiv]

• Explaining Explanations: Axiomatic Feature Interactions for Deep Networks Janizek, Sturmfels, Lee, 2020 [arXiv]
• Explainable AI: A Review of Machine Learning Interpretability Methods
• Explaining Explanations: An Overview of Interpretability of Machine Learning
• How Important Is a Neuron?, Kedar Dhamdhere, Mukund Sundararajan, Qiqi Yan, Google Research [arXiv]
• https://cloud.google.com/explainable-ai
• https://github.com/keyurfaldu/AIgrads

Evaluations

evaluation methods for RS

• Predicting Online Performance of News Recommender Systems Through Richer Evaluation Metrics
• RecSys2018 tutorial

System

Recommendation systems references, and hashing function for flow allocations

Company	Conference	Paper
Tencent	SIGMOD'15	TencentRec: Real-time stream recommendation in practice
Uber	PAPIs'16	Scaling Machine Learning as a Service
Google	KDD'17	TFX: A TensorFlow-Based Production-Scale Machine Learning

Applications

Feeds RecSys

• News
• Pictures
• Videos (PGC, UGC)
• Musics
• e-commerce
• financial products

Computational Ad

• Computational advertising systems

Marketing Growth

• CVR prediction
• LTV prediction

Reference

• 《计算广告论文、学习资料、业界分享》https://github.com/wzhe06/Ad-papers

• 《Must-read papers on Recommender System》https://github.com/hongleizhang/RSPapers

• 《A review and evaluation of CTR prediction models》https://github.com/anyai/OpenCTR

• 《Easy-to-use,Modular and Extendible package of deep-learning based CTR models》https://github.com/shenweichen/DeepCTR

• 《CTR预估深度模型演化之路》https://mp.weixin.qq.com/s/jpWS9ec0MCO4ncSZx38r3w

• Conferences: AAAI、KDD、ICML、WWW、RecSys