Diversified Interactive Recommendation with Implicit Feedback
Explore this paper's citation graph
Summary
A novel diversified recommendation model, named Diversified Contextual Combinatorial Bandit (DC2B), is proposed for interactive recommendation with users' implicit feedback that employs determinantal point process in the recommendation procedure to promote diversity of the recommendation results.
- Type
- article
- Published
- 2020-04-03
- Cited by
- 68
- References
- 34
- Access
- Open access
- OpenAlex
- https://openalex.org/W2997672513
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:212643929
Keywords
Recommender system, Computer science, Regret, Inference, Diversity (politics)
References
- Modeling User Exposure in Recommendation
- Collaborative Filtering beyond the User-Item Matrix
- Personalized Recommendation via Parameter-Free Contextual Bandits
- Interactive Recommender Systems: Tutorial
- The Use of MMR, Diversity-Based Reranking for Reordering Documents and Producing Summaries
- Interactive collaborative filtering
- Avoiding monotony: improving the diversity of recommendation lists
- Solving the apparent diversity-accuracy dilemma of recommender systems
- A contextual-bandit approach to personalized news article recommendation
- Determinantal Point Processes for Machine Learning
- Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms
- Learning to Optimize via Posterior Sampling
- Improving Aggregate Recommendation Diversity Using Ranking-Based Techniques
- Variational Inference: A Review for Statisticians
- Contextual Combinatorial Bandit and its Application on Diversified Online Recommendation
- Promoting Diversity in Recommendation by Entropy Regularizer
- A Framework for Recommending Relevant and Diverse Items
- Diversity in recommender systems - A survey
- Learning to Recommend Accurate and Diverse Items
- Factorization Bandits for Interactive Recommendation
Cited by
- Diversity-Promoting Deep Reinforcement Learning for Interactive Recommendation
- A Hybrid Bandit Framework for Diversified Recommendation
- Advances and Challenges in Conversational Recommender Systems: A Survey
- A Regularized Model to Trade-off between Accuracy and Diversity in a News Recommender System
- Enhancing Domain-Level and User-Level Adaptivity in Diversified Recommendation
- Learning Hierarchical Review Graph Representations for Recommendation
- Matching Algorithms: Fundamentals, Applications and Challenges
- FG-RS: Capture user fine-grained preferences through attribute information for Recommender Systems
- SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations
- Tripartite Collaborative Filtering with Observability and Selection for Debiasing Rating Estimation on Missing-Not-at-Random Data
- Cross-Domain Recommendation based on Heterogeneous information network with Adversarial learning
- Graph Convolutional Matrix Completion via Relation Reconstruction
- Dynamic Graph Construction for Improving Diversity of Recommendation
- Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation
- Personalized Clinical Pathway Recommendation via Attention Based Pre-training
- Dual Preference Distribution Learning for Item Recommendation
- EMDKG: Improving Accuracy-Diversity Trade-Off in Recommendation with EM-based Model and Knowledge Graph Embedding
- End-to-end Learnable Diversity-aware News Recommendation
- TryonCM2: Try-on-Enhanced Fashion Compatibility Modeling Framework
- Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Related papers
- Optimal Regret Analysis of Thompson Sampling in Stochastic Multi-armed Bandit Problem with Multiple Plays
- Lenient Regret for Multi-Armed Bandits
- A Dynamic Observation Strategy for Multi-agent Multi-armed Bandit Problem
- Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits