推薦系統(tǒng)（RS）主要是指應(yīng)用協(xié)同智能（collaborative intelligence）做推薦的技術(shù)，解決了用戶在面對大量信息時無法從中獲得對自己真正有用的那部分信息的問題。

相較于搜索引擎，推薦系統(tǒng)可以根據(jù)用戶的信息需求、興趣等，將用戶感興趣的信息、產(chǎn)品等推薦給用戶，非常的個性化。

目前，推薦系統(tǒng)已經(jīng)廣泛應(yīng)用于很多領(lǐng)域，與之相關(guān)的研究成果也非常多，在今年的KDD 2023 會議錄用論文中，與推薦系統(tǒng)相關(guān)的論文數(shù)目十分可觀。

KDD 的含金量就不用學(xué)姐多說了吧，今年的 KDD 2023 大會共公布了8篇獲獎?wù)撐摹＞唧w可看學(xué)姐之前的文章《KDD 2023 獲獎?wù)撐娜窒?！找?shù)據(jù)挖掘方向idea的進(jìn)》

這次和大家分享的是KDD 2023 會議錄用的71篇推薦系統(tǒng)論文，學(xué)姐把論文目錄整理在下面了，有需要原文+代碼合集的同學(xué)看這里??

掃碼添加小享，回復(fù)“KDD推薦系統(tǒng)”??

免費獲取全部論文+代碼合集

論文list：

• Improving Conversational Recommendation Systems via Counterfactual Data Simulation

• LATTE: A Framework for Learning Item-Features to Make a Domain-Expert for Effective Conversational Recommendation

• Delving into Global Dialogue Structures: Structure Planning Augmented Response Selection for Multi-turn Conversations

• User-Regulation Deconfounded Conversational Recommender System with Bandit Feedback

• Path-Specific Counterfactual Fairness for Recommender Systems

• Meta Multi-agent Exercise Recommendation: A Game Application Perspective

• Shilling Black-box Review-based Recommender Systems through Fake Review Generation

• Privacy Matters: Vertical Federated Linear Contextual Bandits for Privacy Protected Recommendation

• Generative Flow Network for Listwise Recommendation

• PSLOG: Pretraining with Search Logs for Document Ranking

• Text Is All You Need: Learning Language Representations for Sequential Recommendation

• MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction

• Cognitive Evolutionary Search to Select Feature Interactions for Click-Through Rate Prediction

• PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement

• Efficient Bi-Level Optimization for Recommendation Denoising

• Adaptive Disentangled Transformer for Sequential Recommendation

• Meta Graph Learning for Long-tail Recommendation

• Graph Neural Bandits

• E-commerce Search via Content Collaborative Graph Neural Network

• Criteria Tell You More than Ratings: Criteria Preference-Aware Light Graph Convolution for Effective Multi-Criteria Recommendation

• Knowledge Graph Self-Supervised Rationalization for Recommendation

• On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering

• Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay

• Hierarchical Invariant Learning for Domain Generalization Recommendation

• UCEpic: Unifying Aspect Planning and Lexical Constraints for Generating Explanations in Recommendation

• Debiasing Recommendation by Learning Identifiable Latent Confounders

• Reconsidering Learning Objectives in Unbiased Recommendation: A Distribution Shift Perspective

• Who Should Be Given Incentives? Counterfactual Optimal Treatment Regimes Learning for Recommendation

• Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction

• A Sublinear Time Algorithm for Opinion Optimization in Directed Social Networks via Edge Recommendation

• Contrastive Learning for User Sequence Representation in Personalized Product Search

• A Collaborative Transfer Learning Framework for Cross-domain Recommendation

• Building Self-Adaptive Recommendation Models via Responsive Error Compensation Loop

• UA-FedRec: Untargeted Attack on Federated News Recommendation

• PrivateRec: Differentially Private Model Training and Online Serving for Federated News Recommendation

• Doctor Specific Tag Recommendation for Online Medical Record Management

• Hierarchical Projection Enhanced Multi-behavior Recommendation

• Improving Training Stability for Multitask Ranking Models in Recommender Systems

• AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations

• SAMD: An Industrial Framework for Heterogeneous Multi-Scenario Recommendation

• TransAct: Transformer-based Realtime User Action Model for Recommendation at Pinterest

• Controllable Multi-Objective Re-ranking with Policy Hypernetworks

• M5: Multi-Modal Multi-Interest Multi-Scenario Matching for Over-the-Top Recommendation

• CT4Rec: Simple yet Effective Consistency Training for Sequential Recommendation

• Multi-channel Integrated Recommendation with Exposure Constraints

• Graph-Based Model-Agnostic Data Subsampling for Recommendation Systems

• On-device Integrated Re-ranking with Heterogeneous Behavior Modeling

• Variance Reduction Using In-Experiment Data: Efficient and Targeted Online Measurement for Sparse and Delayed Outcomes

• Fresh Content Needs More Attention: Multi-funnel Fresh Content Recommendation

• VRDU: A Benchmark for Visually-rich Document Understanding

• PGLBox: Multi-GPU Graph Learning Framework for Web-Scale Recommendation

• Counterfactual Video Recommendation for Duration Debiasing

• Exploiting Intent Evolution in E-commercial Query Recommendation

• Workplace Recommendation with Temporal Network Objectives

• A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification

• Modeling Dual Period-Varying Preferences for Takeaway Recommendation

• SentiGOLD: A Large Bangla Gold Standard Multi-Domain Sentiment Analysis Dataset and its Evaluation

• Empowering Long-tail Item Recommendation through Cross Decoupling Network (CDN)

• Stationary Algorithmic Balancing Over Dynamic Email Re-Ranking Problem

• Revisiting Neural Retrieval on Accelerators

• Contrastive Learning of Stress-specific Word Embedding for Social Media based Stress Detection

• Adaptive Graph Contrastive Learning for Recommendation

• BOSS: A Bilateral Occupational-Suitability-Aware Recommender System for Online Recruitment

• Tree based Progressive Regression Model for Watch-Time Prediction in Short-video Recommendation

• PIER: Permutation-Level Interest-Based End-to-End Re-ranking Framework in E-commerce

• Constrained Social Community Recommendation

• Scenario-Adaptive Feature Interaction for Click-Through Rate Prediction

• TWIN: TWo-stage Interest Network for Lifelong User Behavior Modeling in CTR Prediction at Kuaishou

• BERT4CTR: An Efficient Framework to Combine Pre-trained Language Model with Non-textual Features for CTR Prediction

• Capturing Conversion Rate Fluctuation during Sales Promotions: A Novel Historical Data Reuse Approach

• Unbiased Delayed Feedback Label Correction for Conversion Rate Prediction

掃碼添加小享，回復(fù)“KDD推薦系統(tǒng)”??

免費獲取全部論文+代碼合集