README_EN.md

Summary of Papers Related to Recommendation System

Introduce

1. Up to 2022-11-25, 486 papers related to recommendation system have been collected and summarized in this repo, including: Match, Pre-Rank, Rank, Re-Rank, Multi-Task, Multi-Scenario, Multi-Modal, Cold-Start, Calibration, Debias, Diversity, Fairness, Feedback-Delay, Distillation, Contrastive Learning, Casual Inference, Look-Alike, Learning-to-Rank, ReinForce Learning and other fields, the repo will track the industry progress and update continuely.
2. Due to the restriction of special characters in the file name, all : in the title of the paper are changed to -. Bring to attention please when searching.
3. If the prefix of the file name contains [], it indicates that I have read it thoroughly. The first [] refers to the publication year of the paper, the second [] refers to the institution or company (optional), and the third [] refers to the abbreviation of the model or the method proposed in the paper (optional).
4. Below some of the primary categories, there are several secondary categories; A paper may involve multiple secondary categories (e.g., Match by Contrastive Learning), and eventually I will put the paper in the main category. The classification will be adjusted and optimized at any time, welcome to put forward any opinions in the issue.
5. If you are the author of the article and do not want your paper to exhibit here, please mention it in the issue. I will remove it immediately after verification.
6. About some Rank Algorithm implementation, please see another repo of mine: https://github.com/tangxyw/RecAlgorithm.
7. This repo is for exchange and study only, without any commercial purpose.

WeChat

Catalogue

• Rank
• Industry
• Pre-Rank
• Re-Rank
• Match
• Multi-Task
• Multi-Modal
• Multi-Scenario
• Debias
• Calibration
• Distillation
• Feedback-Delay
• ContrastiveLearning
• Cold-Start
• Learning-to-Rank
• Fairness
• Look-Alike
• CausalInference
• Diversity
• ABTest
• Reinforce

Rank

• [2009][BPR] Bayesian Personalized Ranking from Implicit Feedback
• [2010][FM] Factorization Machines
• [2014][Facebook][GBDT+LR] Practical Lessons from Predicting Clicks on Ads at Facebook
• [2016][UCL][FNN] Deep Learning over Multi-field Categorical Data
• [2016][Microsft][Deep Crossing] Deep Crossing - Web-Scale Modeling without Manually Crafted Combinatorial Features
• [2016][Google][Wide&Deep] Wide & Deep Learning for Recommender Systems
• [2016][SJTU][PNN] Product-based Neural Networks for User Response Prediction
• [2016][NTU][FFM] Field-aware Factorization Machines for CTR Prediction
• [2017][Stanford][DCN] Deep & Cross Network for Ad Click Predictions
• [2017][NUS][NFM] Neural Factorization Machines for Sparse Predictive Analytics
• [2017][ZJU][AFM] Attentional Factorization Machines - Learning the Weight of Feature Interactions via Attention Networks
• [2017][NUS][NCF] Neural Collaborative Filtering
• [2017][Alibaba][MLR] Learning Piece-wise Linear Models from Large Scale Data for Ad Click Prediction
• [2017][Huawei][DeepFM] A Factorization-Machine based Neural Network for CTR Prediction
• [2018][USTC][xDeepFM] xDeepFM - Combining Explicit and Implicit Feature Interactions for Recommender Systems
• [2019][AutoInt] AutoInt - Automatic Feature Interaction Learning via Self-Attentive Neural Networks
• [2020][Tencent][DFN] Deep Feedback Network for Recommendation
• SESSION-BASED RECOMMENDATIONS WITH RECURRENT NEURAL NETWORKS

Industry

• [2016][Youtube] Deep Neural Networks for YouTube Recommendations
• [2016][Microsoft] User Fatigue in Online News Recommendation
• [2017][Alibaba][DIN] Deep Interest Network for Click-Through Rate Prediction
• [2017][Alibaba][ATRank] ATRank - An Attention-Based User Behavior Modeling Framework for Recommendation
• [2018][Alibaba][DIEN] Deep Interest Evolution Network for Click-Through Rate Prediction
• [2018][FwFM] Field-weighted Factorization Machines for Click-Through Rate Prediction in Display Advertising
• [2018][Airbnb] Real-time Personalization using Embeddings for Search Ranking at Airbnb
• [2019][Alibaba][DSIN] Deep Session Interest Network for Click-Through Rate Prediction
• [2019][Alibaba][BST] Behavior Sequence Transformer for E-commerceRecommendation in Alibaba
• [2019][Weibo][FiBiNET] FiBiNET - Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction
• [2019][Alibaba][MIMN] Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction
• [2019][Airbnb] Applying Deep Learning To Airbnb Search
• [2020][Alibaba][CAN] CAN - Revisiting Feature Co-Action for Click-Through Rate Prediction
• [2020][Alibaba][ESAM] ESAM - Discriminative Domain Adaptation with Non-Displayed Items to Improve Long-Tail Performance
• [2020][Alibaba][SIM] Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
• [2020][Alibaba][DMR] Deep Match to Rank Model for Personalized Click-Through Rate Prediction
• [2021][Fliggy] [DMSN] Spatial-Temporal Deep Intention Destination Networks for Online Travel Planning
• [2021][Huawei][AutoDis] An Embedding Learning Framework for Numerical Features in CTR Prediction
• [2021][Alibaba][DINMP] A Non-sequential Approach to Deep User Interest Model for Click-Through Rate Prediction
• [2021][Google] Bootstrapping Recommendations at Chrome Web Store
• Adversarial Mixture Of Experts with Category Hierarchy Soft Constraint
• Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction
• Curriculum Disentangled Recommendation with Noisy Multi-feedback
• Category-Specific CNN for Visual-aware CTR Prediction at JD.com
• ContextNet - A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding
• CAEN - A Hierarchically Attentive Evolution Network for Item-Attribute-Change-Aware Recommendation in the Growing E-commerce Environment
• Dual Graph enhanced Embedding Neural Network for CTR Prediction
• Deep Interest with Hierarchical Attention Network for Click-Through Rate Prediction
• Disentangling Past-Future Modeling in Sequential Recommendation via Dual Networks
• Deep Learning Recommendation Model for Personalization and Recommendation System
• Deep Spatio-Temporal Neural Networks for Click-Through Rate Prediction
• Denoising Neural Network for News Recommendation with Positive and Negative Implicit Feedback
• Denoising User-aware Memory Network for Recommendation
• EXTR - Click-Through Rate Prediction with Externalities in E-Commerce Sponsored Search
• End-to-End User Behavior Retrieval in Click-Through Rate Prediction Model
• FM2 - Field-matrixed Factorization Machines for Recommender Systems
• FeedRec - News Feed Recommendation with Various User Feedbacks
• Fi-GNN - Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
• FLEN - Leveraging Field for Scalable CTR Prediction
• FiBiNet++ - Improving FiBiNet by Greatly Reducing Model Size for CTR Prediction
• GateNet - Gating-Enhanced Deep Network for Click-Through Rate Prediction
• Hybrid Interest Modeling for Long-tailed Users
• HIEN - Hierarchical Intention Embedding Network for Click-Through Rate Prediction
• Improving Recommendation Quality in Google Drive
• Improving Deep Learning For Airbnb Search
• Implicit User Awareness Modeling via Candidate Items for CTR Prediction in Search Ads
• Long Short-Term Temporal Meta-learning in Online Recommendation
• LambdaFM - Learning Optimal Ranking with Factorization Machines Using Lambda Surrogates
• Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
• Learning Within-Session Budgets from Browsing Trajectories
• Modeling Users’ Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search
• MaskNet - Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask
• Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction
• MRIF - Multi-resolution Interest Fusion for Recommendation
• News Recommendation with Candidate-aware User Modeling
• Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data
• PURS - Personalized Unexpected Recommender System for Improving User Satisfaction
• Recommender Transformers with Behavior Pathways
• Res-embedding for Deep Learning Based Click-Through Rate Prediction Modeling
• Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce
• Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction
• Triangle Graph Interest Network for Click-through Rate Prediction
• TencentRec - Real-time Stream Recommendation in Practice
• TiSSA - A Time Slice Self-Attention Approach for Modeling Sequential User Behaviors
• Towards Understanding the Overfitting Phenomenon of Deep Click-Through Rate Prediction Models
• User Behavior Retrieval for Click-Through Rate Prediction

TriggerInduced

• [2021][Tencent][R3S] Real-time Relevant Recommendation Suggestion
• [2022][Alibaba][DIHN] Deep Interest Highlight Network for Click-Through Rate Prediction in Trigger-Induced Recommendation

Reciprocal

• [2022][Boss][DPGNN] Modeling Two-Way Selection Preference for Person-Job Fit
• Latent Factor Models and Aggregation Operators for Collaborative Filtering in Reciprocal Recommender Systems
• MATCHING THEORY-BASED RECOMMENDER SYSTEMS IN ONLINE DATING
• Optimally balancing receiver and recommended users' importance in reciprocal recommender systems
• Reciprocal Recommendation for Job Matching with Bidirectional Feedback
• Reciprocal Recommendation System for Online Dating
• RECON - A Reciprocal Recommender for Online Dating
• Reciprocal Recommendation Algorithm for the Field of Recruitment
• Supporting users in fnding successful matches in reciprocal recommender systems

Dataset

• KuaiRand - An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos
• KuaiRec - A Fully-observed Dataset and Insights for Evaluating Recommender Systems
• Tenrec - A Large-scale Multipurpose Benchmark Dataset for Recommender Systems

Bundle

• Bundle Recommendation with Graph Convolutional Networks
• CrossCBR - Cross-view Contrastive Learning for Bundle Recommendation
• Hierarchical Fashion Graph Network for Personalized Outfit Recommendation

Edge

• Real-time Short Video Recommendation on Mobile Devices

POI

• [2020][meituan][STGCN] STGCN - A Spatial-Temporal Aware Graph Learning Method for POI Recommendation
• A Survey on Deep Learning Based Point-Of-Interest (POI) Recommendations
• A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals
• Empowering Next POI Recommendation with Multi-Relational Modeling
• Hierarchical Multi-Task Graph Recurrent Network for Next POI Recommendation
• LightMove - A Lightweight Next-POI Recommendation for Taxicab Rooftop Advertising
• Modeling Spatio-temporal Neighbourhood for Personalized Point-of-interest Recommendation
• Next Point-of-Interest Recommendation with Inferring Multi-step Future Preferences
• Online POI Recommendation - Learning Dynamic Geo-Human Interactions in Streams
• Point-of-Interest Recommender Systems based on Location-Based Social Networks - A Survey from an Experimental Perspective
• POINTREC - A Test Collection for Narrative-driven Point of Interest Recommendation
• Personalized Long- and Short-term Preference Learning for Next POI Recommendation
• ST-PIL - Spatial-Temporal Periodic Interest Learning for Next Point-of-Interest Recommendation
• TADSAM - A Time-Aware Dynamic Self-Attention Model for Next Point-of-Interest Recommendation
• Why We Go Where We Go - Profiling User Decisions on Choosing POIs
• Where to Go Next - Modeling Long- and Short-Term User Preferences for Point-of-Interest Recommendation
• You Are What and Where You Are - Graph Enhanced Attention Network for Explainable POI Recommendation

Intent

• Automatically Discovering User Consumption Intents in Meituan
• FINN - Feedback Interactive Neural Network for Intent Recommendation
• Metapath-guided Heterogeneous Graph Neural Network for Intent Recommendation

Representation

• [2022][Pinterest][PinnerFormer] PinnerFormer - Sequence Modeling for User Representation at Pinterest

FeatureHashing

• [2021][Google][DHE] Learning to Embed Categorical Features without Embedding Tables for Recommendation
• Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems
• Feature Hashing for Large Scale Multitask Learning
• Getting Deep Recommenders Fit - Bloom Embeddings for Sparse Binary Input Output Networks
• Hash Embeddings for Efficient Word Representations
• Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
• Memory-efficient Embedding for Recommendations
• Model Size Reduction Using Frequency Based Double Hashing for Recommender Systems

Regression

• [2014][Yahoo] Beyond Clicks - Dwell Time for Personalization
• Deconfounding Duration Bias in Watch-time Prediction for Video Recommendation

Pre-Rank

• [2020][Alibaba][COLD] COLD - Towards the Next Generation of Pre-Ranking System
• [2021][Alibaba] Towards a Better Tradeoff between Effectiveness and Efficiency in Pre-Ranking - A Learnable Feature Selection based Approach
• [2022] On Ranking Consistency of Pre-ranking Stage
• AutoFAS - Automatic Feature and Architecture Selection for Pre-Ranking System
• Cascade Ranking for Operational E-commerce Search
• Contrastive Information Transfer for Pre-Ranking Systems
• EENMF - An End-to-End Neural Matching Framework for E-Commerce Sponsored Search

Re-Rank

• [2018][Hulu] Fast Greedy MAP Inference for Determinantal Point Process to Improve Recommendation Diversity
• [2020][LinkedIn] Ads Allocation in Feed via Constrained Optimization
• Cross DQN - Cross Deep Q Network for Ads Allocation in Feed
• Coverage, Redundancy and Size-Awareness in Genre Diversity for Recommender Systems
• GenDeR - A Generic Diversified Ranking Algorithm
• GRN - Generative Rerank Network for Context-wise Recommendation
• Globally Optimized Mutual Influence Aware Ranking in E-Commerce Search
• Learning a Deep Listwise Context Model for Ranking Refinement
• Neural Re-ranking in Multi-stage Recommender Systems - A Review
• Practical Diversified Recommendations on YouTube with Determinantal Point Processes
• Personalized Click Shaping through Lagrangian Duality for Online Recommendation
• Personalized Re-ranking for Recommendation
• Personalized Complementary Product Recommendation
• Personalized Re-ranking with Item Relationships for E-commerce
• Re-ranking With Constraints on Diversified Exposures for Homepage Recommender System
• Revisit Recommender System in the Permutation Prospective
• SLATEQ - A Tractable Decomposition for Reinforcement Learning with Recommendation Sets
• Seq2slate - Re-ranking and slate optimization with rnns
• Sliding Spectrum Decomposition for Diversified Recommendation
• The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries
• User Response Models to Improve a REINFORCE Recommender System

Match

• [2015][Microsoft][DSSM in Recsys] A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems
• [2015][Sceptre] Inferring Networks of Substitutable and Complementary Products
• [2016][Yahoo][App2Vec] App2Vec - Vector Modeling of Mobile Apps and Applications
• [2018][TC-CML] Loss Aversion in Recommender Systems - Utilizing Negative User Preference to Improve Recommendation Quality
• [2019][Google] Sampling-Bias-Corrected Neural Modeling for Large Corpus Item Recommendations
• [2019][Baidu][MOBIUS] MOBIUS - Towards the Next Generation of Query-Ad Matching in Baidu’s Sponsored Search
• [2019][Alibaba][SDM] SDM - Sequential Deep Matching Model for Online Large-scale Recommender System
• [2020][Alibaba][Swing&Surprise] Large Scale Product Graph Construction for Recommendation in E-commerce
• [2020][Weixin][UTPM] Learning to Build User-tag Profile in Recommendation System
• [2020][Facebook][EBR] Embedding-based Retrieval in Facebook Search
• [2020][Google][MNS] Mixed Negative Sampling for Learning Two-tower Neural Networks in Recommendations
• [2021][Google] Self-supervised Learning for Large-scale Item Recommendations
• [2021][Alibaba][MGDSPR] Embedding-based Product Retrieval in Taobao Search
• Attentive Collaborative Filtering - Multimedia Recommendation with Item- and Component-Level A�ention
• Attentive Sequential Models of Latent Intent for Next Item Recommendation
• A User-Centered Concept Mining System for Query and Document Understanding at Tencent
• AutoRec - Autoencoders Meet Collaborative Filtering
• A Dual Augmented Two-tower Model for Online Large-scale Recommendation
• CROLoss - Towards a Customizable Loss for Retrieval Models in Recommender Systems
• Collaborative Denoising Auto-Encoders for Top-N Recommender Systems
• Coarse-to-Fine Sparse Sequential Recommendation
• Cross-Batch Negative Sampling for Training Two-Tower Recommenders
• Collaborative Deep Learning for Recommender Systems
• Deep Matrix Factorization Models for Recommender Systems
• Disentangled Self-Supervision in Sequential Recommenders
• Deep Collaborative Filtering via Marginalized Denoising Auto-encoder
• Efficient Training on Very Large Corpora via Gramian Estimation
• Extreme Multi-label Learning for Semantic Matching in Product Search
• Factorization Meets the Neighborhood - a Multifaceted Collaborative Filtering Model
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• Heterogeneous Graph Neural Networks for Large-Scale Bid Keyword Matching
• Itinerary-aware Personalized Deep Matching at Fliggy
• Improving Recommendation Accuracy using Networks of Substitutable and Complementary Products
• ItemSage - Learning Product Embeddings for Shopping Recommendations at Pinterest
• Latent Relational Metric Learning via Memory-based Attention for Collaborative Ranking
• Learning Deep Structured Semantic Models for Web Search using Clickthrough Data
• Locker - Locally Constrained Self-Attentive Sequential Recommendation
• NAIS - Neural Attentive Item Similarity Model for Recommendation
• Octopus - Comprehensive and Elastic User Representation for the Generation of Recommendation Candidates
• Outer Product-based Neural Collaborative Filtering
• PinnerSage - Multi-Modal User Embedding Framework for Recommendations at Pinterest
• Path-based Deep Network for Candidate Item Matching in Recommenders
• Representing and Recommending Shopping Baskets with Complementarity, Compatibility, and Loyalty
• Recommendation on Live - Streaming Platforms- Dynamic Availability and Repeat Consumption
• Sequential Recommendation via Stochastic Self-Attention
• Sparse-Interest Network for Sequential Recommendation
• Self-Attentive Sequential Recommendation
• StarSpace - Embed All The Things!
• Towards Personalized and Semantic Retrieval - An End-to-End Solution for E-commerce Search via Embedding Learning
• Uni-Retriever - Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search
• Variational Autoencoders for Collaborative Filtering
• XDM - Improving Sequential Deep Matching with Unclicked User Behaviors for Recommender System

Tree-Based

• Deep Retrieval - Learning A Retrievable Structure for Large-Scale Recommendations
• Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
• Learning Optimal Tree Models under Beam Search
• Learning Tree-based Deep Model for Recommender Systems

Nearline

• Truncation-Free Matching System for Display Advertising at Alibaba

Classic

• Collaborative Filtering Recommender Systems
• GroupLens - An open architecture for collaborative filtering of Netnews
• Item-Based Collaborative Filtering Recommendation Algorithms

Mulit-Interset

• [2019][Alibaba][MIND] Multi-Interest Network with Dynamic Routing for Recommendation at Tmall
• [2020][Alibaba][ComiRec] Controllable Multi-Interest Framework for Recommendation
• Every Preference Changes Differently - Neural Multi-Interest Preference Model with Temporal Dynamics for Recommendation
• Improving Multi-Interest Network with Stable Learning
• Multiple Interest and Fine Granularity Network for User Modeling

GNN

• [2014][word2vec] Negative-Sampling Word-Embedding Method
• [2014][DeepWalk] DeepWalk - Online Learning of Social Representations
• [2015][Microsoft][LINE] LINE - Large-scale Information Network Embedding
• [2016][SDNE] Structural Deep Network Embedding
• [2016][Stanford][node2vec] node2vec - Scalable Feature Learning for Networks
• [2016][word2vec] word2vec Parameter Learning Explained
• [2016][item2vec] ITEM2VEC - NEURAL ITEM EMBEDDING FOR COLLABORATIVE FILTERING
• [2017][GCN] SEMI-SUPERVISED CLASSIFICATION WITH GRAPH CONVOLUTIONAL NETWORKS
• [2017][Stanford][GraphSage] Inductive Representation Learning on Large Graphs
• [2018][GAT] GRAPH ATTENTION NETWORKS
• [2018][Alibaba] Learning and Transferring IDs Representation in E-commerce
• [2018][Pinterest][PinSage] Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• [2018][Etsy] Learning Item-Interaction Embeddings for User Recommendations
• [2018][Alibaba][EGES] Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba
• [2019][SR-GNN] Session-based Recommendation with Graph Neural Networks
• [2019][NGCF]Neural Graph Collaborative Filtering
• [2020][LightGCN] LightGCN - Simplifying and Powering Graph Convolution Network for Recommendation
• ATBRG - Adaptive Target-Behavior Relational Graph Network for Effective Recommendation
• Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View
• Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer
• Debiasing Neighbor Aggregation for Graph Neural Network in Recommender Systems
• DC-GNN - Decoupled Graph Neural Networks for Improving and Accelerating Large-Scale E-commerce Retrieval
• Disentangled Graph Collaborative Filtering
• Decoupled Graph Convolution Network for Inferring Substitutable and Complementary Items
• Embedding-based News Recommendationfor Millions of Users
• Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction
• Friend Recommendations with Self-Rescaling Graph Neural Networks
• FASTGCN - FAST LEARNING WITH GRAPH CONVOLUTIONAL NETWORKS VIA IMPORTANCE SAMPLING
• Graph Convolutional Matrix Completion
• Graph Neural Networks for Friend Ranking in Large-scale Social Platforms
• Graph Intention Network for Click-through Rate Prediction in Sponsored Search
• Graph Neural Network for Tag Ranking in Tag-enhanced Video Recommendation
• Graph Neural Networks for Social Recommendation
• GraphSAIL - Graph Structure Aware Incremental Learning for Recommender Systems
• Improving Accuracy and Diversity in Matching of Recommendation with Diversified Preference Network
• IntentGC - a Scalable Graph Convolution Framework Fusing Heterogeneous Information for Recommendation
• MultiSage - Empowering GCN with Contextualized Multi-Embeddings on Web-Scale Multipartite Networks
• MMGCN - Multi-modal Graph Convolution Network for Personalized Recommendation of Micro-video
• M2GRL - A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
• Network Embedding as Matrix Factorization - Unifying DeepWalk, LINE, PTE, and node2vec
• Neighbor Interaction Aware Graph Convolution Networks for Recommendation
• Package Recommendation with Intra- and Inter-Package Attention Networks
• ProNE - Fast and Scalable Network Representation Learning
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Revisiting Item Promotion in GNN-based Collaborative Filtering - A Masked Targeted Topological Attack Perspective
• Self-supervised Graph Learning for Recommendation
• SVD-GCN - A Simplified Graph Convolution Paradigm for Recommendation
• Self-Supervised Hypergraph Transformer for Recommender Systems
• TwHIN - Embedding the Twitter Heterogeneous Information Network for Personalized Recommendation
• metapath2vec - Scalable Representation Learning for Heterogeneous Networks
• struc2vec - Learning Node Representations from Structural Identity

Multi-Task

• [2012][MGDA] Multiple-gradient descent algorithm (MGDA) for multiobjective optimization
• [2018][Alibaba][ESMM] Entire Space Multi-Task Model - An Effective Approach for Estimating Post-Click Conversion Rate
• [2018][MagicLeap][GradNorm] GradNorm - Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
• [2018][Google][MMOE] Modeling Task Relationships in Multi-task Learning with Multi-gate Mixture-of-Experts
• [2018][Cambridge] Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
• [2019][Alibaba][DBMTL] Deep Bayesian Multi-Target Learning for Recommender Systems
• [2019][Intel] Multi-Task Learning as Multi-Objective Optimization
• [2019][Youtube] Recommending What Video to Watch Next - A Multitask Ranking System
• [2019][Alibaba] A Pareto-Efficient Algorithm for Multiple Objective Optimization in E-Commerce Recommendation
• [2020][Alibaba][Multi-IPW&Multi-DR] LARGE-SCALE CAUSAL APPROACHES TO DEBIASING POST-CLICK CONVERSION RATE ESTIMATION WITH MULTI-TASK LEARNING
• [2020][Tencent][PLE] Progressive Layered Extraction (PLE) - A Novel Multi-Task Learning (MTL) Model for Personalized Recommendations
• [2020][Google][MoSE] Multitask Mixture of Sequential Experts for User Activity Streams
• [2020][JD][DMT] Deep Multifaceted Transformers for Multi-objective Ranking in Large-Scale E-commerce Recommender Systems
• [2020][PCGrad] Gradient Surgery for Multi-Task Learning
• [2021][Meituan][AITM] Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising
• [2022][Alibaba][ESCM2] ESCM2 - Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimation
• Can Small Heads Help Understanding and Improving Multi-Task Generalization
• Dynamic Task Prioritization for Multitask Learning
• DSelect-k - Differentiable Selection in the Mixture of Experts with Applications to Multi-Task Learning
• Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction
• GemNN - Gating-Enhanced Multi-Task Neural Networks with Feature Interaction Learning for CTR Prediction
• Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Prediction
• HyperGrid Transformers - Towards A Single Model for Multiple Tasks
• Learning to Recommend with Multiple Cascading Behaviors
• MetaBalance - Improving Multi-Task Recommendations via Adapting Gradient Magnitudes of Auxiliary Tasks
• MSSM - A Multiple-level Sparse Sharing Model for Efficient Multi-Task Learning
• Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling
• Multi-Objective Ranking Optimization for Product Search Using Stochastic Label Aggregation
• Multi-Task Learning for Dense Prediction Tasks - A Survey
• Multi-Task Learning as Multi-Objective Optimization - slide
• Perceive Your Users in Depth - Learning Universal User Representations from Multiple E-commerce Tasks
• Personalized Approximate Pareto-Efficient Recommendation
• Pareto Multi-Task Learning
• SNR - Sub-Network Routing for Flexible Parameter Sharing in Multi-Task Learning
• Understanding and Improving Fairness-Accuracy Trade-offs in Multi-Task Learning
• Why I like it - multi-task learning for recommendation and explanation

Multi-Modal

• Adversarial Multimodal Representation Learning for Click-Through Rate Prediction
• Pretraining Representations of Multi-modal Multi-query E-commerce Search

Multi-Scenario

• [2020][JD][DADNN] DADNN - Multi-Scene CTR Prediction via Domain-Aware Deep Neural Network
• [2021][Alibaba][STAR] One Model to Serve All - Star Topology Adaptive Recommenderfor Multi-Domain CTR Prediction
• A Deep Framework for Cross-Domain and Cross-System Recommendations
• APG - Adaptive Parameter Generation Network for Click-Through Rate Prediction
• AdaSparse - Learning Adaptively Sparse Structures for Multi-Domain Click-Through Rate Prediction
• A Survey on Cross-domain Recommendation - Taxonomies, Methods, and Future Directions
• Automatic Expert Selection for Multi-Scenario and Multi-Task Search
• Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks
• Cross-Domain Recommendation - An Embedding and Mapping Approach
• CoNet - Collaborative Cross Networks for Cross-Domain Recommendation
• Cross-domain Recommendation Without Sharing User-relevant Data
• Continual Transfer Learning for Cross-Domain Click-Through Rate Prediction at Taobao
• DTCDR - A Framework for Dual-Target Cross-Domain Recommendation
• Dynamic collaborative filtering Thompson Sampling for cross-domain advertisements recommendation
• DeepAPF - Deep Attentive Probabilistic Factorization for Multi-site Video Recommendation
• Improving Multi-Scenario Learning to Rank in E-commerce by Exploiting Task Relationships in the Label Space
• KEEP - An Industrial Pre-Training Framework for Online Recommendation via Knowledge Extraction and Plugging
• Leaving No One Behind - A Multi-Scenario Multi-Task Meta Learning Approach for Advertiser Modeling
• Multi-Graph based Multi-Scenario Recommendation in Large-scale Online Video Services
• Personalized Transfer of User Preferences for Cross-domain Recommendation
• SAR-Net - A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
• Semi-Supervised Learning for Cross-Domain Recommendation to Cold-Start Users
• Scenario-aware and Mutual-based approach for Multi-scenario Recommendation in E-Commerce
• Self-Supervised Learning on Users’ Spontaneous Behaviors for Multi-Scenario Ranking in E-commerce
• Scenario-Adaptive and Self-Supervised Model for Multi-Scenario Personalized Recommendation

Debias

• [2019][Huawei][PAL] a position-bias aware learning framework for CTR prediction in live recommender systems
• AutoDebias - Learning to Debias for Recommendation
• Bias and Debias in Recommender System - A Survey and Future Directions
• Deep Position-wise Interaction Network for CTR Prediction
• Denoising Implicit Feedback for Recommendation
• DVR - Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
• Disentangling User Interest and Conformity for Recommendation with Causal Embedding
• Improving Micro-video Recommendation by Controlling Position Bias
• Learning to rank with selection bias in personal search
• Unbiased Learning-to-Rank with Biased Feedback

Calibration

• Attended Temperature Scaling - A Practical Approach for Calibrating Deep Neural Networks
• Beyond temperature scaling - Obtaining well-calibrated multiclass probabilities with Dirichlet calibration
• Beta calibration - a well-founded and easily implemented improvement on logistic calibration for binary classifiers
• CALIBRATION OF NEURAL NETWORKS USING SPLINES
• Calibrated Recommendations
• Calibrating User Response Predictions in Online Advertising
• Crank up the volume - preference bias amplificationin collaborative recommendation
• Distribution-free calibration guarantees for histogram binning without sample splitting
• Field-aware Calibration - A Simple and Empirically Strong Method for Reliable Probabilistic Predictions
• Mitigating Bias in Calibration Error Estimation
• Measuring Calibration in Deep Learning
• MBCT - Tree-Based Feature-Aware Binning for Individual Uncertainty Calibration
• On Calibration of Modern Neural Networks
• Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers
• Obtaining Well Calibrated Probabilities Using Bayesian Binning
• Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods
• Posterior Probability Matters - Doubly-Adaptive Calibration for Neural Predictions in Online Advertising
• Transforming Classifier Scores into Accurate Multiclass Probability Estimates

Distillation

• [2021][Tencent][DMTL] Distillation based Multi-task Learning - A Candidate Generation Model for Improving Reading Duration
• Ensembled CTR Prediction via Knowledge Distillation
• Privileged Features Distillation at Taobao Recommendations
• Rocket Launching - A Universal and Efficient Framework for Training Well-performing Light Net
• Ranking Distillation - Learning Compact Ranking Models With High Performance for Recommender System

Feedback-Delay

• [2021][Alibaba] Real Negatives Matter - Continuous Training with Real Negatives for Delayed Feedback Modeling
• Asymptotically Unbiased Estimation for Delayed Feedback Modeling via Label Correction
• An Attention-based Model for Conversion Rate Prediction with Delayed Feedback via Post-click Calibration
• Addressing Delayed Feedback for Continuous Training with Neural Networks in CTR prediction
• A Nonparametric Delayed Feedback Model for Conversion Rate Prediction
• A Feedback Shift Correction in Predicting Conversion Rates under Delayed Feedback
• Counterfactual Reward Modification for Streaming Recommendation with Delayed Feedback
• Capturing Delayed Feedback in Conversion Rate Predictionvia Elapsed-Time Sampling
• Delayed Feedback Model with Negative Binomial Regression for Multiple Conversions
• Delayed Feedback Modeling for the Entire Space Conversion Rate Prediction
• Dual Learning Algorithm for Delayed Conversions
• Handling many conversions per click in modeling delayed feedback
• Modeling Delayed Feedback in Display Advertising

ContrastiveLearning

• An Empirical Study of Training Self-Supervised Vision Transformers
• A Simple Framework for Contrastive Learning of Visual Representations
• Bootstrap Your Own Latent A New Approach to Self-Supervised Learning
• Contrastive Learning for Interactive Recommendation in Fashion
• Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems
• CCL4Rec - Contrast over Contrastive Learning for Micro-video Recommendation
• Disentangled Contrastive Learning for Social Recommendation
• Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning
• Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
• Improved Baselines with Momentum Contrastive Learning
• Multi-view Multi-behavior Contrastive Learning in Recommendation
• Momentum Contrast for Unsupervised Visual Representation Learning
• Multi-level Contrastive Learning Framework for Sequential Recommendation
• Predictive and Contrastive- Dual-Auxiliary Learning for Recommendation
• Understanding the Behaviour of Contrastive Loss
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere

Cold-Start

• [2017][MAML] Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• [2017][DropoutNet] DropoutNet - Addressing Cold Start in Recommender Systems
• [2017][HIN] Heterogeneous Information Network Embedding for Recommendation
• [2020][Wechat][ICAN] Internal and Contextual Attention Network for Cold-start Multi-channel Matching in Recommendation
• [2021][Kuaishou][POSO] POSO - Personalized Cold Start Modules for Large-scale Recommender Systems
• Alleviating Cold-start Problem in CTR Prediction with A Variational Embedding Learning Framework
• Addressing the Item Cold-start Problem by Attribute-driven Active Learning
• A Practical Exploration System for Search Advertising
• A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps
• Cold-start Sequential Recommendation via Meta Learner
• GIFT - Graph-guIded Feature Transfer for Cold-Start Video Click-Through Rate Prediction
• Handling User Cold Start Problem in Recommender Systems Using Fuzzy Clustering
• Learning to Warm Up Cold Item Embeddings for Cold-start Recommendation with Meta Scaling and Shifting Networks
• LHRM - A LBS based Heterogeneous Relations Model for User Cold Start Recommendation in Online Travel Platform
• MAMO - Memory-Augmented Meta-Optimization for Cold-start Recommendation
• Transform Cold-Start Users into Warm via Fused Behaviors in Large-Scale Recommendation
• Telepath - Understanding Users from a Human Vision Perspective in Large-Scale Recommender Systems
• What You Look Matters Offline Evaluation of Advertising Creatives for Cold-start Problem
• Warm Up Cold-start Advertisements - Improving CTR Predictions via Learning to Learn ID Embeddings

Exploration&Exploitation

• An Empirical Evaluation of Thompson Sampling
• Adversarial Gradient Driven Exploration for Deep Click-Through Rate Prediction
• A Contextual-Bandit Approach to Personalized News Article Recommendation
• Comparison-based Conversational Recommender System with Relative Bandit Feedback

MetaLearning

• A Meta-Learning Perspective on Cold-Start Recommendations for Items
• Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Prediction
• Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation
• MeLU - Meta-Learned User Preference Estimator for Cold-Start Recommendation
• Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks
• Preference-Adaptive Meta-Learning for Cold-Start Recommendation
• Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
• Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users

Learning-to-Rank

Pair-wise

• LambdaRank - Learning to Rank with Nonsmooth Cost Functions
• RankNET - Learning to Rank Using Gradient Descent
• RankBoost - An Effcient Boosting Algorithm for Combining Preferences

Point-wise

• Learning to Rank Using Classification and Gradient

List-wise

• AdaRank - A Boosting Algorithm for Information Retrieval
• From RankNet to LambdaRank to LambdaMART
• LambdaMART - Adapting Boosting for Information Retrieval Measures
• ListNet - Learning to Rank - From Pairwise Approach to Listwise Approach

Fairness

• [2020][FairCo] Controlling Fairness and Bias in Dynamic Learning-to-Rank
• Equity of Attention - Amortizing Individual Fairness in Rankings
• Fairness in Recommendation Ranking through Pairwise Comparisons

Look-Alike

• [2019][Tencent][RALM] Real-time Attention Based Look-alike Model for Recommender System
• [2019][Pinterest] Finding Users Who Act Alike - Transfer Learning for Expanding
• A Sub-linear, Massive-scale Look-alike Audience Extension System
• Adversarial Factorization Autoencoder for Look-alike Modeling
• A Feature-Pair-based Associative Classification Approach to Look-alike Modeling for Conversion-Oriented User-Targeting in Tail Campaigns
• Audience Expansion for Online Social Network Advertising
• Comprehensive Audience Expansion based on End-to-End Neural Prediction
• Effective Audience Extension in Online Advertising
• Hubble - An Industrial System for Audience Expansion in Mobile Marketing
• Learning to Expand Audience via Meta Hybrid Experts and Critics for Recommendation and Advertising
• Score Look-alike Audiences
• Two-Stage Audience Expansion for Financial Targeting in Marketing

CausalInference

• CauseRec - Counterfactual User Sequence Synthesis for Sequential Recommendation
• Counterfactual Data-Augmented Sequential Recommendation
• Clicks can be Cheating - Counterfactual Recommendation for Mitigating Clickbait Issue
• Causal Inference in Recommender Systems - A Survey and Future Directions
• Doubly Robust Joint Learning for Recommendation on Data Missing Not at Random
• Deconfounded Recommendation for Alleviating Bias Amplification
• Improving Ad Click Prediction by Considering Non-displayed Events
• Model-Agnostic Counterfactual Reasoning for Eliminating Popularity Bias in Recommender System
• Practical Counterfactual Policy Learning for Top-K Recommendations
• Recommendations as Treatments - Debiasing Learning and Evaluation

Diversity

• [2020][Huawei][pDPP] Personalized Re-ranking for Improving Diversity in Live Recommender Systems
• A Framework for Recommending Accurate and Diverse Items Using Bayesian Graph Convolutional Neural Networks
• Adaptive, Personalized Diversity for Visual Discovery
• Diversity on the Go! Streaming Determinantal Point Processes under a Maximum Induced Cardinality Objective
• DGCN - Diversified Recommendation with Graph Convolutional Networks
• Diversifying Search Results
• Enhancing Recommendation Diversity using Determinantal Point Processes on Knowledge Graphs
• Enhancing Domain-Level and User-Level Adaptivity in Diversified Recommendation
• Exploiting Query Reformulations for Web Search Result Diversification
• Feature-aware Diversified Re-ranking with Disentangled Representations for Relevant Recommendation
• Future-Aware Diverse Trends Framework for Recommendation
• Improving Recommendation Lists Through Topic Diversification
• Managing Diversity in Airbnb Search
• Novelty and Diversity in Information Retrieval Evaluation
• P-Companion - A Principled Framework for Diversified Complementary Product Recommendation
• UNDERSTANDING DIVERSITY IN SESSION-BASED RECOMMENDATION

ABTest

• Overlapping Experiment Infrastructure - More, Better, Faster Experimentation

Reinforce

• Jointly Learning to Recommend and Advertise
• Reinforcement Learning for Slate-based Recommender Systems - A Tractable Decomposition and Practical Methodology
• Top-K Off-Policy Correctionfor a REINFORCE Recommender System