MeLU: Meta-Learned User Preference Estimator for Cold-Start Recommendation

2019/07/31 by Hoyeop Lee, Jinbae Im, Lee, Hoyeop +7 · 17 citations
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Recommender Systems and Techniques #Topic Modeling #cs.AI #cs.IR #cs.LG

paper · pdf · doi:10.48550/arxiv.1908.00413

Accepted as a full paper at KDD 2019

arxiv created 2019/07/31 · openalex publication_date 2019/07/31 · arxiv updated 2019/08/02 · openalex created_date 2019/08/13 · openalex updated_date 2026/07/28

Abstract

This paper proposes a recommender system to alleviate the cold-start problem that can estimate user preferences based on only a small number of items. To identify a user's preference in the cold state, existing recommender systems, such as Netflix, initially provide items to a user; we call those items evidence candidates. Recommendations are then made based on the items selected by the user. Previous recommendation studies have two limitations: (1) the users who consumed a few items have poor recommendations and (2) inadequate evidence candidates are used to identify user preferences. We propose a meta-learning-based recommender system called MeLU to overcome these two limitations. From meta-learning, which can rapidly adopt new task with a few examples, MeLU can estimate new user's preferences with a few consumed items. In addition, we provide an evidence candidate selection strategy that determines distinguishing items for customized preference estimation. We validate MeLU with two benchmark datasets, and the proposed model reduces at least 5.92% mean absolute error than two comparative models on the datasets. We also conduct a user study experiment to verify the evidence selection strategy.

Citations

• Prototypical Networks for Few-shot Learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Meta-SGD: Learning to Learn Quickly for Few-Shot Learning
• Memory Matching Networks for One-Shot Image Recognition

Cited by

• On Recommending Category: A Cascading Approach
• LLM-Empowered Representation Learning for Emerging Item Recommendation
• Event-Aware Prompt Learning for Dynamic Graphs
• ChoirRec: Semantic User Grouping via LLMs for Conversion Rate Prediction of Low-Activity Users
• Retentive Relevance: Capturing Long-Term User Value in Recommendation Systems
• Online Decision Making with Generative Action Sets
• Addressing the Cold-Start Problem for Personalized Combination Drug Screening
• VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results
• EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
• KuaiLive: A Real-time Interactive Dataset for Live Streaming Recommendation
• M²VAE: Multi-Modal Multi-View Variational Autoencoder for Cold-start Item Recommendation
• GREAT: Guiding Query Generation with a Trie for Recommending Related Search about Video at Kuaishou
• A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges
• Universal Reusability in Recommender Systems: The Case for Dataset- and Task-Independent Frameworks
• AliBoost: Ecological Boosting Framework in Alibaba Platform
• The Limits of Graph Samplers for Training Inductive Recommender Systems: Extended results
• Should We Tailor the Talk? Understanding the Impact of Conversational Styles on Preference Elicitation in Conversational Recommender Systems
• Enhancing LLM-based Recommendation through Semantic-Aligned Collaborative Knowledge

Related

• Cold-start Sequential Recommendation via Meta Learner
• Is Meta-Learning the Right Approach for the Cold-Start Problem in Recommender Systems?
• The use of Recommender Systems in web technology and an in-depth analysis of Cold State problem
• Learning to Learn a Cold-start Sequential Recommender
• Personalized Adaptive Meta Learning for Cold-start User Preference Prediction