SIGIR 2022中，有哪些分类的推荐系统论文值得整理？
- 内容介绍
- 文章标签
- 相关推荐
本文共计3352个文字，预计阅读时间需要14分钟。
大家好，我是小白。ACM SIGIR 2022是CCF A类会议，聚焦于人工智能领域的信息检索（IR）方向，是最具权威的国际会议。会议将专注于信息的存储、检索和传播等各个方面，涵盖研究内容。
大家好，我是对白。
ACM SIGIR 2022是CCF A类会议，人工智能领域智能信息检索（ Information Retrieval，IR）方向最权威的国际会议。会议专注于信息的存储、检索和传播等各个方面，包括研究战略、输出方案和系统评估等等。第45届国际计算机学会信息检索大会（The 45rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2022）计划于今年7月11日-7月15日在西班牙马德里召开。这次会议共收到794篇长文和667篇短文投稿，有161篇长文和165篇短文被录用，录用率约为20%和24.7%。官方发布的接收论文列表：
Accepted Paperssigir.org/sigir2022/program/accepted/
本文选取了SIGIR 2022中170篇长文或短文，**重点对推荐系统相关论文（124篇）按不同的任务场景和研究话题进行分类整理，也对其他热门研究方向（问答、对话、知识图谱等，46篇）进行了归类**，以供参考。文章也同步发布在**AI****Box**知乎专栏（知乎搜索「 AI Box专栏」），整理过程中难免有疏漏，欢迎大家在知乎专栏的文章下方评论留言，交流探讨！
从词云图看**今年SIGIR的研究热点**：根据长文和短文的标题绘制如下词云图，可以看到今年研究方向依旧集中在Recommendation，也包括Retrieval、Query等方向；主要任务包括：Ranking、Cross-domain、Multi-Model/Behavior、Few-Shot、User modeling、Conversation等；热门技术包括：Neural Networks、Knowledge Graph、GNN、Contrastive Learning、Transformer等，其中基于Graph的方法依旧是今年的研究热点。
**本文目录**
--------
**1 按照任务场景划分**
* CTR
* Collaborative Filtering
* Sequential/Session-based Recommendation
* Conversational Recommender System
* POI Recommendation
* Cross-domain/Multi-behavior Recommendation
* Knowledge-aware Recommendation
* News Recommendation
* Others
**2 按照主要技术划分**
* GNN-based
* RL-based
* Contrastive Learning based
* AutoML-based
* Others
**3 按照研究话题划分**
* Bias/Debias in Recommender System
* Explanation in Recommender System
* Long-tail/Cold-start in Recommender System
* Fairness in Recommender System
* Diversity in Recommender System
* Attack/Denoise in Recommender System
* Others
**4 其他研究方向**
* QA
* Knowledge Graph
* Conversation/ Dialog
* Summarization
* Multi-Modality
* Generation
* Representation Learning
* * *
**1.按照任务场景划分**
--------------
### **1.1 CTR /CVR Prediction**
1. Enhancing CTR Prediction with Context-Aware Feature Representation Learning
2. HIEN: Hierarchical Intention Embedding Network for Click-Through Rate Prediction
3. NAS-CTR: Efficient Neural Architecture Search for Click-Through Rate Prediction
4. NMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
5. Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer
6. Neural Statistics for Click-Through Rate Prediction
7. Smooth-AUC: Smoothing the Path Towards Rank-based CTR Prediction
8. DisenCTR: Dynamic Graph-based Disentangled Representation for Click-Through Rate Prediction
9. Deep Multi-Representational Item Network for CTR Prediction
10. Gating-adapted Wavelet Multiresolution Analysis for Exposure Sequence Modeling in CTR prediction
11. MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios
12. Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction
13. Clustering based Behavior Sampling with Long Sequential Data for CTR Prediction
14. CTnoCVR: A Novelty Auxiliary Task Making the Lower-CTR-Higher-CVR Upper
### **1.2 Collaborative Filtering**
1. Geometric Disentangled Collaborative Filtering
2. Self-Augmented Recommendation with Hypergraph Contrastive Collaborative Filtering
3. Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering
4. Unify Local and Global Information for Top-N Recommendation
5. Enhancing Top-N Item Recommendations by Peer Collaboration
6. Evaluation of Herd Behavior Caused by Population-scale Concept Drift in Collaborative Filtering
### **1.3 Sequential/Session-based Recommendations**
1. Decoupled Side Information Fusion for Sequential Recommendation
2. On-Device Next-Item Recommendation with Self-Supervised Knowledge Distillation
3. Multi-Agent RL-based Information Selection Model for Sequential Recommendation
4. An Attribute-Driven Mirroring Graph Network for Session-based Recommendation
5. When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation
6. Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation
7. AutoGSR: Neural Architecture Search for Graph-based Session Recommendation
8. Ada-Ranker: A Data Distribution Adaptive Ranking Paradigm for Sequential Recommendation
9. Multi-Faceted Global Item Relation Learning for Session-Based Recommendation
10. ReCANet: A Repeat Consumption-Aware Neural Network for Next Basket Recommendation in Grocery Shopping
11. Determinantal Point Process Set Likelihood-Based Loss Functions for Sequential Recommendation
12. Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
13. Coarse-to-Fine Sparse Sequential Recommendation
14. Dual Contrastive Network for Sequential Recommendation
15. Explainable Session-based Recommendation with Meta-Path Guided Instances and Self-Attention Mechanism
16. Item-Provider Co-learning for Sequential Recommendation
17. RESETBERT4Rec: A Pre-training Model Integrating Time And User Historical Behavior for Sequential Recommendation
18. Enhancing Hypergraph Neural Networks with Intent Disentanglement for Session-based Recommendation
19. CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space
20. DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation
21. Progressive Self-Attention Network with Unsymmetrical Positional Encoding for Sequential Recommendation
22. ELECRec: Training Sequential Recommenders as Discriminators
23. Exploiting Session Information in BERT-based Session-aware Sequential Recommendation
### **1.4 Conversational Recommender System**
1. Learning to Infer User Implicit Preference in Conversational Recommendation
2. User-Centric Conversational Recommendation with Multi-Aspect User Modeling
3. Variational Reasoning about User Preferences for Conversational Recommendation
4. Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems
5. Improving Conversational Recommender Systems via Transformer-based Sequential Modelling
6. Conversational Recommendation via Hierarchical Information Modeling
### **1.5 POI Recommendation**
1. Hierarchical Multi-Task Graph Recurrent Network for Next POI Recommendation
2. Learning Graph-based Disentangled Representations for Next POI Recommendation
3. GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
4. Next Point-of-Interest Recommendation with Auto-Correlation Enhanced Multi-Modal Transformer Network
5. Empowering Next POI Recommendation with Multi-Relational Modeling
### **1.6 Cross-domain/Multi-behavior Recommendation**
1. Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders
2. DisenCDR: Learning Disentangled Representations for Cross-Domain Recommendation
3. Doubly-Adaptive Reinforcement Learning for Cross-Domain Interactive Recommendation
4. Exploiting Variational Domain-Invariant User Embedding for Partially Overlapped Cross Domain Recommendation
5. Multi-Behavior Sequential Transformer Recommender
### **1.7 Knowledge-aware Recommendation**
1. Knowledge Graph Contrastive Learning for Recommendation
2. Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
3. Alleviating Spurious Correlations in Knowledge-aware Recommendations through Counterfactual Generator
4. HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
5. KETCH: Knowledge Graph Enhanced Thread Recommendation in Healthcare Forums
### **1.8 News Recommendation**
1. ProFairRec: Provider Fairness-aware News Recommendation
2. Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
3. FUM: Fine-grained and Fast User Modeling for News Recommendation
4. Is News Recommendation a Sequential Recommendation Task?
5. News Recommendation with Candidate-aware User Modeling
6. MM-Rec: Visiolinguistic Model Empowered Multimodal News Recommendation
### **1.9 others**
1. CAPTOR: A Crowd-Aware Pre-Travel Recommender System for Out-of-Town Users
2. PERD: Personalized Emoji Recommendation with Dynamic User Preference
3. Item Similarity Mining for Multi-Market Recommendation
4. A Content Recommendation Policy for Gaining Subscribers
5. Thinking inside The Box: Learning Hypercube Representations for Group Recommendation
**2.按照主要技术划分**
--------------
### **2.1 GNN-based**
1. Hierarchical Multi-Task Graph Recurrent Network for Next POI Recommendation
2. An Attribute-Driven Mirroring Graph Network for Session-based Recommendation
3. Co-clustering Interactions via Attentive Hypergraph Neural Network
4. Graph Trend Filtering Networks for Recommendation
5. EFLEC: Efficient Feature-LEakage Correction in GNN based Recommendation Systems
6. DH-HGCN: Dual Homogeneity Hypergraph Convolutional Network for Multiple Social Recommendations
7. Enhancing Hypergraph Neural Networks with Intent Disentanglement for Session-based Recommendation
8. DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation
### **2.2 RL-based**
1. Locality-Sensitive State-Guided Experience Replay Optimization for Sparse-Reward in Online Recommendation
2. Multi-Agent RL-based Information Selection Model for Sequential Recommendation
3. Rethinking Reinforcement Learning for Recommendation: A Prompt Perspective
4. Doubly-Adaptive Reinforcement Learning for Cross-Domain Interactive Recommendation
5. MGPolicy: Meta Graph Enhanced Off-policy Learning for Recommendations
6. Value Penalized Q-Learning for Recommender Systems
7. Revisiting Interactive Recommender System with Reinforcement Learning
### **2.3 Contrastive Learning based**
1. A Review-aware Graph Contrastive Learning Framework for Recommendation
2. Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
3. Knowledge Graph Contrastive Learning for Recommendation
4. Self-Augmented Recommendation with Hypergraph Contrastive Collaborative Filtering
5. Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
6. Dual Contrastive Network for Sequential Recommendation
7. Improving Micro-video Recommendation via Contrastive Multiple Interests
8. An MLP-based Algorithm for Efficient Contrastive Graph Recommendations
9. Multi-modal Graph Contrastive Learning for Micro-video Recommendation
10. Towards Results-level Proportionality for Multi-objective Recommender Systems
11. Socially-aware Dual Contrastive Learning for Cold-Start Recommendation
### **2.4 AutoML-based Recommender System**
1. Single-shot Embedding Dimension Search in Recommender System
2. AutoLossGen: Automatic Loss Function Generation for Recommender Systems
3. NAS-CTR: Efficient Neural Architecture Search for Click-Through Rate Prediction
### **2.5 Others**
1. Forest-based Deep Recommender
2. Deployable and Continuable Meta-Learning-Based Recommender System with Fast User-Incremental Updates
**3.按照研究话题划分**
--------------
### **3.1 Bias/Debias in Recommender System**
1. Interpolative Distillation for Unifying Biased and Debiased Recommendation
2. Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders
3. Bilateral Self-unbiased Recommender Learning from Biased Implicit Feedback
4. Mitigating Consumer Biases in Recommendations with Adversarial Training
5. Neutralizing Popularity Bias in Recommendation Models
6. DeSCoVeR: Debiased Semantic Context Prior for Venue Recommendation
### **3.2 Explanation in Recommender System**
1. Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations
2. PEVAE: A hierarchical VAE for personalized explainable recommendation.
3. Explainable Session-based Recommendation with Meta-Path Guided Instances and Self-Attention Mechanism
### **3.3 Long-tail/Cold-start in Recommender System**
1. Socially-aware Dual Contrastive Learning for Cold-Start Recommendation
2. Transform Cold-Start Users into Warm via Fused Behaviors in Large-Scale Recommendation
3. Generative Adversarial Framework for Cold-Start Item Recommendation
4. Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder
### **3.4 Fairness in Recommender System**
1. Joint Multisided Exposure Fairness for Recommendation
2. ProFairRec: Provider Fairness-aware News Recommendation
3. CPFair: Personalized Consumer and Producer Fairness Re-ranking for Recommender Systems
4. Explainable Fairness for Feature-aware Recommender Systems
5. Selective Fairness in Recommendation via Prompts
6. Regulating Provider Groups Exposure in Recommendations
### **3.5 Diversity in Recommender System**
1. DAWAR: Diversity-aware Web APIs Recommendation for Mashup Creation based on Correlation Graph
2. Mitigating the Filter Bubble while Maintaining Relevance: Targeted Diversification with VAE-based Recommender Systems
3. Diversity vs Relevance: a practical multi-objective study in luxury fashion recommendations
### **3.6 Attack/Denoise in Recommender System**
1. Learning to Denoise Unreliable Interactions for Graph Collaborative Filtering
2. Less is More: Reweighting Important Spectral Graph Features for Recommendation
3. Denoising Time Cycle Modeling for Recommendation
4. Adversarial Graph Perturbations for Recommendations at Scale
### **3.7Others**
1. Privacy-Preserving Synthetic Data Generation for Recommendation
2. User-Aware Multi-Interest Learning for Candidate Matching in Recommenders
3. User-controllable Recommendation Against Filter Bubbles
4. Rethinking Correlation-based Item-Item Similarities for Recommender Systems
5. ReLoop: A Self-Correction Learning Loop for Recommender Systems
6. Towards Results-level Proportionality for Multi-objective Recommender Systems
**4.其他研究方向**
------------
### **4.1 QA**
1. DGQAN: Dual Graph Question-Answer Attention Networks for Answer Selection
2. Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion
3. PTAU: Prompt Tuning for Attributing Unanswerable Questions
4. Conversational Question Answering on Heterogeneous Sources
5. A Non-Factoid Question-Answering Taxonomy
6. QUASER: Question Answering with Scalable Extractive Rationalization
7. Detecting Frozen Phrases in Open-Domain Question Answering
8. Answering Count Query with Explanatory Evidence
### **4.1 Knowledge Graph**
1. Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
2. Incorporating Context Graph with Logical Reasoning for Inductive Relation Prediction
3. Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding
4. Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective
5. Relation-Guided Few-Shot Relational Triple Extraction
### **4.2 Conversation/ Dialog**
1. Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation
2. Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy
3. COSPLAY: Concept Set Guided Personalized Dialogue System
4. Understanding User Satisfaction with Task-Oriented Dialogue Systems
5. A Multi-Task Based Neural Model to Simulate Users in Goal Oriented Dialogue Systems
6. Task-Oriented Dialogue System as Natural Language Generation
### **4.3 Summarization**
1. HTKG: Deep Keyphrase Generation with Neural Hierarchical Topic Guidance
2. V2P: Vision-to-Prompt based Multi-Modal Product Summary Generation
3. Unifying Cross-lingual Summarization and Machine Translation with Compression Rate
4. ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge Disentanglement
5. Summarizing Legal Regulatory Documents using Transformers
6. QSG Transformer: Transformer with Query-Attentive Semantic Graph for Query-Focused Summarization
7. MuchSUM: Multi-channel Graph Neural Network for Extractive Summarization
8. Lightweight Meta-Learning for Low-Resource Abstractive Summarization
9. Extractive Elementary Discourse Units for Improving Abstractive Summarization
### **4.4 Multi-Modality**
1. Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities
2. Progressive Learning for Image Retrieval with Hybrid-Modality Queries
3. CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
4. Multimodal Entity Linking with Gated Hierarchical Fusion and Contrastive Training
5. CRET: Cross-Modal Retrieval Transformer for Efficient Text-Video Retrieval
6. Bit-aware Semantic Transformer Hashing for Multi-modal Retrieval
7. Video Moment Retrieval from Text Queries via Single Frame Annotation
8. Multimodal Disentanglement Variational AutoEncoders for Zero-Shot Cross-Modal Retrieval
9. A Multitask Framework for Sentiment, Emotion and Sarcasm aware Cyberbullying Detection in Multi-modal Code-Mixed Memes
10. Animating Images to transfer CLIP for Video-Text Retrieval
11. Image-Text Retrieval via Contrastive Learning with Auxiliary Generative Features and Support-set Regularization
12. An Efficient Fusion Mechanism for Multimodal Low-resource Setting
### **4.5 Generation**
1. Mutual Disentanglement Learning for Joint Fine-Grained Sentiment Classification and Controllable Text Generation
2. Target-aware Abstractive Related Work Generation with Contrastive Learning
3. Generating Clarifying Questions with Web Search Results
4. Choosing The Right Teammate For Cooperative Text Generation
### **4.6 Representation Learning**
1. Structure and Semantics Preserving Document Representations
2. Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders
最后欢迎大家关注我的**微信公众号：** [对白的算法屋](link.zhihu.com/?target=mp.weixin.qq.com/s?__biz=Mzg3NzY2ODIzOA==&mid=2247485704&idx=1&sn=b35bcfa95aca965dd7ae654aaa22ca39&chksm=cf1e3be9f869b2ff71aad632b60206ff041877b3753238e2998a4aa1a18c46889270574cb84c&token=1884889230&lang=zh_CN%23rd)（**duibainotes**），跟踪NLP、推荐系统和对比学习等机器学习领域前沿，日常还会分享我的创业心得和人生感悟。想进一步交流的同学也可以通过公众号加我的微信，和我一同探讨技术问题，谢谢！
本文共计3352个文字，预计阅读时间需要14分钟。
大家好，我是小白。ACM SIGIR 2022是CCF A类会议，聚焦于人工智能领域的信息检索（IR）方向，是最具权威的国际会议。会议将专注于信息的存储、检索和传播等各个方面，涵盖研究内容。
大家好，我是对白。
ACM SIGIR 2022是CCF A类会议，人工智能领域智能信息检索（ Information Retrieval，IR）方向最权威的国际会议。会议专注于信息的存储、检索和传播等各个方面，包括研究战略、输出方案和系统评估等等。第45届国际计算机学会信息检索大会（The 45rd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2022）计划于今年7月11日-7月15日在西班牙马德里召开。这次会议共收到794篇长文和667篇短文投稿，有161篇长文和165篇短文被录用，录用率约为20%和24.7%。官方发布的接收论文列表：
Accepted Paperssigir.org/sigir2022/program/accepted/
本文选取了SIGIR 2022中170篇长文或短文，**重点对推荐系统相关论文（124篇）按不同的任务场景和研究话题进行分类整理，也对其他热门研究方向（问答、对话、知识图谱等，46篇）进行了归类**，以供参考。文章也同步发布在**AI****Box**知乎专栏（知乎搜索「 AI Box专栏」），整理过程中难免有疏漏，欢迎大家在知乎专栏的文章下方评论留言，交流探讨！
从词云图看**今年SIGIR的研究热点**：根据长文和短文的标题绘制如下词云图，可以看到今年研究方向依旧集中在Recommendation，也包括Retrieval、Query等方向；主要任务包括：Ranking、Cross-domain、Multi-Model/Behavior、Few-Shot、User modeling、Conversation等；热门技术包括：Neural Networks、Knowledge Graph、GNN、Contrastive Learning、Transformer等，其中基于Graph的方法依旧是今年的研究热点。
**本文目录**
--------
**1 按照任务场景划分**
* CTR
* Collaborative Filtering
* Sequential/Session-based Recommendation
* Conversational Recommender System
* POI Recommendation
* Cross-domain/Multi-behavior Recommendation
* Knowledge-aware Recommendation
* News Recommendation
* Others
**2 按照主要技术划分**
* GNN-based
* RL-based
* Contrastive Learning based
* AutoML-based
* Others
**3 按照研究话题划分**
* Bias/Debias in Recommender System
* Explanation in Recommender System
* Long-tail/Cold-start in Recommender System
* Fairness in Recommender System
* Diversity in Recommender System
* Attack/Denoise in Recommender System
* Others
**4 其他研究方向**
* QA
* Knowledge Graph
* Conversation/ Dialog
* Summarization
* Multi-Modality
* Generation
* Representation Learning
* * *
**1.按照任务场景划分**
--------------
### **1.1 CTR /CVR Prediction**
1. Enhancing CTR Prediction with Context-Aware Feature Representation Learning
2. HIEN: Hierarchical Intention Embedding Network for Click-Through Rate Prediction
3. NAS-CTR: Efficient Neural Architecture Search for Click-Through Rate Prediction
4. NMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
5. Neighbour Interaction based Click-Through Rate Prediction via Graph-masked Transformer
6. Neural Statistics for Click-Through Rate Prediction
7. Smooth-AUC: Smoothing the Path Towards Rank-based CTR Prediction
8. DisenCTR: Dynamic Graph-based Disentangled Representation for Click-Through Rate Prediction
9. Deep Multi-Representational Item Network for CTR Prediction
10. Gating-adapted Wavelet Multiresolution Analysis for Exposure Sequence Modeling in CTR prediction
11. MetaCVR: Conversion Rate Prediction via Meta Learning in Small-Scale Recommendation Scenarios
12. Adversarial Filtering Modeling on Long-term User Behavior Sequences for Click-Through Rate Prediction
13. Clustering based Behavior Sampling with Long Sequential Data for CTR Prediction
14. CTnoCVR: A Novelty Auxiliary Task Making the Lower-CTR-Higher-CVR Upper
### **1.2 Collaborative Filtering**
1. Geometric Disentangled Collaborative Filtering
2. Self-Augmented Recommendation with Hypergraph Contrastive Collaborative Filtering
3. Investigating Accuracy-Novelty Performance for Graph-based Collaborative Filtering
4. Unify Local and Global Information for Top-N Recommendation
5. Enhancing Top-N Item Recommendations by Peer Collaboration
6. Evaluation of Herd Behavior Caused by Population-scale Concept Drift in Collaborative Filtering
### **1.3 Sequential/Session-based Recommendations**
1. Decoupled Side Information Fusion for Sequential Recommendation
2. On-Device Next-Item Recommendation with Self-Supervised Knowledge Distillation
3. Multi-Agent RL-based Information Selection Model for Sequential Recommendation
4. An Attribute-Driven Mirroring Graph Network for Session-based Recommendation
5. When Multi-Level Meets Multi-Interest: A Multi-Grained Neural Model for Sequential Recommendation
6. Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation
7. AutoGSR: Neural Architecture Search for Graph-based Session Recommendation
8. Ada-Ranker: A Data Distribution Adaptive Ranking Paradigm for Sequential Recommendation
9. Multi-Faceted Global Item Relation Learning for Session-Based Recommendation
10. ReCANet: A Repeat Consumption-Aware Neural Network for Next Basket Recommendation in Grocery Shopping
11. Determinantal Point Process Set Likelihood-Based Loss Functions for Sequential Recommendation
12. Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
13. Coarse-to-Fine Sparse Sequential Recommendation
14. Dual Contrastive Network for Sequential Recommendation
15. Explainable Session-based Recommendation with Meta-Path Guided Instances and Self-Attention Mechanism
16. Item-Provider Co-learning for Sequential Recommendation
17. RESETBERT4Rec: A Pre-training Model Integrating Time And User Historical Behavior for Sequential Recommendation
18. Enhancing Hypergraph Neural Networks with Intent Disentanglement for Session-based Recommendation
19. CORE: Simple and Effective Session-based Recommendation within Consistent Representation Space
20. DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation
21. Progressive Self-Attention Network with Unsymmetrical Positional Encoding for Sequential Recommendation
22. ELECRec: Training Sequential Recommenders as Discriminators
23. Exploiting Session Information in BERT-based Session-aware Sequential Recommendation
### **1.4 Conversational Recommender System**
1. Learning to Infer User Implicit Preference in Conversational Recommendation
2. User-Centric Conversational Recommendation with Multi-Aspect User Modeling
3. Variational Reasoning about User Preferences for Conversational Recommendation
4. Analyzing and Simulating User Utterance Reformulation in Conversational Recommender Systems
5. Improving Conversational Recommender Systems via Transformer-based Sequential Modelling
6. Conversational Recommendation via Hierarchical Information Modeling
### **1.5 POI Recommendation**
1. Hierarchical Multi-Task Graph Recurrent Network for Next POI Recommendation
2. Learning Graph-based Disentangled Representations for Next POI Recommendation
3. GETNext: Trajectory Flow Map Enhanced Transformer for Next POI Recommendation
4. Next Point-of-Interest Recommendation with Auto-Correlation Enhanced Multi-Modal Transformer Network
5. Empowering Next POI Recommendation with Multi-Relational Modeling
### **1.6 Cross-domain/Multi-behavior Recommendation**
1. Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders
2. DisenCDR: Learning Disentangled Representations for Cross-Domain Recommendation
3. Doubly-Adaptive Reinforcement Learning for Cross-Domain Interactive Recommendation
4. Exploiting Variational Domain-Invariant User Embedding for Partially Overlapped Cross Domain Recommendation
5. Multi-Behavior Sequential Transformer Recommender
### **1.7 Knowledge-aware Recommendation**
1. Knowledge Graph Contrastive Learning for Recommendation
2. Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
3. Alleviating Spurious Correlations in Knowledge-aware Recommendations through Counterfactual Generator
4. HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation
5. KETCH: Knowledge Graph Enhanced Thread Recommendation in Healthcare Forums
### **1.8 News Recommendation**
1. ProFairRec: Provider Fairness-aware News Recommendation
2. Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
3. FUM: Fine-grained and Fast User Modeling for News Recommendation
4. Is News Recommendation a Sequential Recommendation Task?
5. News Recommendation with Candidate-aware User Modeling
6. MM-Rec: Visiolinguistic Model Empowered Multimodal News Recommendation
### **1.9 others**
1. CAPTOR: A Crowd-Aware Pre-Travel Recommender System for Out-of-Town Users
2. PERD: Personalized Emoji Recommendation with Dynamic User Preference
3. Item Similarity Mining for Multi-Market Recommendation
4. A Content Recommendation Policy for Gaining Subscribers
5. Thinking inside The Box: Learning Hypercube Representations for Group Recommendation
**2.按照主要技术划分**
--------------
### **2.1 GNN-based**
1. Hierarchical Multi-Task Graph Recurrent Network for Next POI Recommendation
2. An Attribute-Driven Mirroring Graph Network for Session-based Recommendation
3. Co-clustering Interactions via Attentive Hypergraph Neural Network
4. Graph Trend Filtering Networks for Recommendation
5. EFLEC: Efficient Feature-LEakage Correction in GNN based Recommendation Systems
6. DH-HGCN: Dual Homogeneity Hypergraph Convolutional Network for Multiple Social Recommendations
7. Enhancing Hypergraph Neural Networks with Intent Disentanglement for Session-based Recommendation
8. DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation
### **2.2 RL-based**
1. Locality-Sensitive State-Guided Experience Replay Optimization for Sparse-Reward in Online Recommendation
2. Multi-Agent RL-based Information Selection Model for Sequential Recommendation
3. Rethinking Reinforcement Learning for Recommendation: A Prompt Perspective
4. Doubly-Adaptive Reinforcement Learning for Cross-Domain Interactive Recommendation
5. MGPolicy: Meta Graph Enhanced Off-policy Learning for Recommendations
6. Value Penalized Q-Learning for Recommender Systems
7. Revisiting Interactive Recommender System with Reinforcement Learning
### **2.3 Contrastive Learning based**
1. A Review-aware Graph Contrastive Learning Framework for Recommendation
2. Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendation
3. Knowledge Graph Contrastive Learning for Recommendation
4. Self-Augmented Recommendation with Hypergraph Contrastive Collaborative Filtering
5. Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
6. Dual Contrastive Network for Sequential Recommendation
7. Improving Micro-video Recommendation via Contrastive Multiple Interests
8. An MLP-based Algorithm for Efficient Contrastive Graph Recommendations
9. Multi-modal Graph Contrastive Learning for Micro-video Recommendation
10. Towards Results-level Proportionality for Multi-objective Recommender Systems
11. Socially-aware Dual Contrastive Learning for Cold-Start Recommendation
### **2.4 AutoML-based Recommender System**
1. Single-shot Embedding Dimension Search in Recommender System
2. AutoLossGen: Automatic Loss Function Generation for Recommender Systems
3. NAS-CTR: Efficient Neural Architecture Search for Click-Through Rate Prediction
### **2.5 Others**
1. Forest-based Deep Recommender
2. Deployable and Continuable Meta-Learning-Based Recommender System with Fast User-Incremental Updates
**3.按照研究话题划分**
--------------
### **3.1 Bias/Debias in Recommender System**
1. Interpolative Distillation for Unifying Biased and Debiased Recommendation
2. Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders
3. Bilateral Self-unbiased Recommender Learning from Biased Implicit Feedback
4. Mitigating Consumer Biases in Recommendations with Adversarial Training
5. Neutralizing Popularity Bias in Recommendation Models
6. DeSCoVeR: Debiased Semantic Context Prior for Venue Recommendation
### **3.2 Explanation in Recommender System**
1. Post Processing Recommender Systems with Knowledge Graphs for Recency, Popularity, and Diversity of Explanations
2. PEVAE: A hierarchical VAE for personalized explainable recommendation.
3. Explainable Session-based Recommendation with Meta-Path Guided Instances and Self-Attention Mechanism
### **3.3 Long-tail/Cold-start in Recommender System**
1. Socially-aware Dual Contrastive Learning for Cold-Start Recommendation
2. Transform Cold-Start Users into Warm via Fused Behaviors in Large-Scale Recommendation
3. Generative Adversarial Framework for Cold-Start Item Recommendation
4. Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder
### **3.4 Fairness in Recommender System**
1. Joint Multisided Exposure Fairness for Recommendation
2. ProFairRec: Provider Fairness-aware News Recommendation
3. CPFair: Personalized Consumer and Producer Fairness Re-ranking for Recommender Systems
4. Explainable Fairness for Feature-aware Recommender Systems
5. Selective Fairness in Recommendation via Prompts
6. Regulating Provider Groups Exposure in Recommendations
### **3.5 Diversity in Recommender System**
1. DAWAR: Diversity-aware Web APIs Recommendation for Mashup Creation based on Correlation Graph
2. Mitigating the Filter Bubble while Maintaining Relevance: Targeted Diversification with VAE-based Recommender Systems
3. Diversity vs Relevance: a practical multi-objective study in luxury fashion recommendations
### **3.6 Attack/Denoise in Recommender System**
1. Learning to Denoise Unreliable Interactions for Graph Collaborative Filtering
2. Less is More: Reweighting Important Spectral Graph Features for Recommendation
3. Denoising Time Cycle Modeling for Recommendation
4. Adversarial Graph Perturbations for Recommendations at Scale
### **3.7Others**
1. Privacy-Preserving Synthetic Data Generation for Recommendation
2. User-Aware Multi-Interest Learning for Candidate Matching in Recommenders
3. User-controllable Recommendation Against Filter Bubbles
4. Rethinking Correlation-based Item-Item Similarities for Recommender Systems
5. ReLoop: A Self-Correction Learning Loop for Recommender Systems
6. Towards Results-level Proportionality for Multi-objective Recommender Systems
**4.其他研究方向**
------------
### **4.1 QA**
1. DGQAN: Dual Graph Question-Answer Attention Networks for Answer Selection
2. Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion
3. PTAU: Prompt Tuning for Attributing Unanswerable Questions
4. Conversational Question Answering on Heterogeneous Sources
5. A Non-Factoid Question-Answering Taxonomy
6. QUASER: Question Answering with Scalable Extractive Rationalization
7. Detecting Frozen Phrases in Open-Domain Question Answering
8. Answering Count Query with Explanatory Evidence
### **4.1 Knowledge Graph**
1. Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
2. Incorporating Context Graph with Logical Reasoning for Inductive Relation Prediction
3. Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding
4. Re-thinking Knowledge Graph Completion Evaluation from an Information Retrieval Perspective
5. Relation-Guided Few-Shot Relational Triple Extraction
### **4.2 Conversation/ Dialog**
1. Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation
2. Interacting with Non-Cooperative User: A New Paradigm for Proactive Dialogue Policy
3. COSPLAY: Concept Set Guided Personalized Dialogue System
4. Understanding User Satisfaction with Task-Oriented Dialogue Systems
5. A Multi-Task Based Neural Model to Simulate Users in Goal Oriented Dialogue Systems
6. Task-Oriented Dialogue System as Natural Language Generation
### **4.3 Summarization**
1. HTKG: Deep Keyphrase Generation with Neural Hierarchical Topic Guidance
2. V2P: Vision-to-Prompt based Multi-Modal Product Summary Generation
3. Unifying Cross-lingual Summarization and Machine Translation with Compression Rate
4. ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge Disentanglement
5. Summarizing Legal Regulatory Documents using Transformers
6. QSG Transformer: Transformer with Query-Attentive Semantic Graph for Query-Focused Summarization
7. MuchSUM: Multi-channel Graph Neural Network for Extractive Summarization
8. Lightweight Meta-Learning for Low-Resource Abstractive Summarization
9. Extractive Elementary Discourse Units for Improving Abstractive Summarization
### **4.4 Multi-Modality**
1. Tag-assisted Multimodal Sentiment Analysis under Uncertain Missing Modalities
2. Progressive Learning for Image Retrieval with Hybrid-Modality Queries
3. CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
4. Multimodal Entity Linking with Gated Hierarchical Fusion and Contrastive Training
5. CRET: Cross-Modal Retrieval Transformer for Efficient Text-Video Retrieval
6. Bit-aware Semantic Transformer Hashing for Multi-modal Retrieval
7. Video Moment Retrieval from Text Queries via Single Frame Annotation
8. Multimodal Disentanglement Variational AutoEncoders for Zero-Shot Cross-Modal Retrieval
9. A Multitask Framework for Sentiment, Emotion and Sarcasm aware Cyberbullying Detection in Multi-modal Code-Mixed Memes
10. Animating Images to transfer CLIP for Video-Text Retrieval
11. Image-Text Retrieval via Contrastive Learning with Auxiliary Generative Features and Support-set Regularization
12. An Efficient Fusion Mechanism for Multimodal Low-resource Setting
### **4.5 Generation**
1. Mutual Disentanglement Learning for Joint Fine-Grained Sentiment Classification and Controllable Text Generation
2. Target-aware Abstractive Related Work Generation with Contrastive Learning
3. Generating Clarifying Questions with Web Search Results
4. Choosing The Right Teammate For Cooperative Text Generation
### **4.6 Representation Learning**
1. Structure and Semantics Preserving Document Representations
2. Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders
最后欢迎大家关注我的**微信公众号：** [对白的算法屋](link.zhihu.com/?target=mp.weixin.qq.com/s?__biz=Mzg3NzY2ODIzOA==&mid=2247485704&idx=1&sn=b35bcfa95aca965dd7ae654aaa22ca39&chksm=cf1e3be9f869b2ff71aad632b60206ff041877b3753238e2998a4aa1a18c46889270574cb84c&token=1884889230&lang=zh_CN%23rd)（**duibainotes**），跟踪NLP、推荐系统和对比学习等机器学习领域前沿，日常还会分享我的创业心得和人生感悟。想进一步交流的同学也可以通过公众号加我的微信，和我一同探讨技术问题，谢谢！