Meta-Prod2Vec - Product Embeddings Using Side-Information for Recommendation

Abstract

We propose Meta-Prod2vec, a novel method to compute item similarities for recommendation that leverages existing item metadata. Such scenarios are frequently encountered in applications such as content recommendation, ad targeting and web search. Our method leverages past user interactions with items and their attributes to compute low-dimensional embeddings of items. Specifically, the item metadata is in- jected into the model as side information to regularize the item embeddings. We show that the new item representa- tions lead to better performance on recommendation tasks on an open music dataset.

References in corpus (7)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Distributed Representations of Sentences and Documents
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Wide & Deep Learning for Recommender Systems
• Metadata Embeddings for User and Item Cold-start Recommendations
• Hierarchical Neural Language Models for Joint Representation of Streaming Documents and their Content

Cited by in corpus (22)

• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• Recommender Systems in the Era of Large Language Models (LLMs)
• Evaluation of Session-based Recommendation Algorithms
• Causal Embeddings for Recommendation
• A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research
• Conditional Generation Net for Medication Recommendation
• Customer Lifetime Value Prediction Using Embeddings
• TADOC: Text Analytics Directly on Compression
• Product Knowledge Graph Embedding for E-commerce
• Representation Learning and Pairwise Ranking for Implicit Feedback in Recommendation Systems
• Institutional Collaboration Recommendation: An expertise-based framework using NLP and Network Analysis
• M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations
• Tuning Word2vec for Large Scale Recommendation Systems
• Beyond NDCG: behavioral testing of recommender systems with RecList
• Knowledge-aware Complementary Product Representation Learning
• A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services
• Conceptual Organization is Revealed by Consumer Activity Patterns
• DMBGN: Deep Multi-Behavior Graph Networks for Voucher Redemption Rate Prediction
• LightSAGE: Graph Neural Networks for Large Scale Item Retrieval in Shopee's Advertisement Recommendation
• Relaxed Softmax for learning from Positive and Unlabeled data
• Pretrained Embeddings for E-commerce Machine Learning: When it Fails and Why?
• DiskJoin: Large-scale Vector Similarity Join with SSD