TransNets: Learning to Transform for Recommendation
arXiv:1704.02298 · doi:10.1145/3109859.3109878
Abstract
Recently, deep learning methods have been shown to improve the performance of recommender systems over traditional methods, especially when review text is available. For example, a recent model, DeepCoNN, uses neural nets to learn one latent representation for the text of all reviews written by a target user, and a second latent representation for the text of all reviews for a target item, and then combines these latent representations to obtain state-of-the-art performance on recommendation tasks. We show that (unsurprisingly) much of the predictive value of review text comes from reviews of the target user for the target item. We then introduce a way in which this information can be used in recommendation, even when the target user's review for the target item is not available. Our model, called TransNets, extends the DeepCoNN model by introducing an additional latent layer representing the target user-target item pair. We then regularize this layer, at training time, to be similar to another latent representation of the target user's review of the target item. We show that TransNets and extensions of it improve substantially over the previous state-of-the-art.
Accepted for publication in the 11th ACM Conference on Recommender Systems (RecSys 2017)
References in corpus (5)
Cited by in corpus (36)
- Deep Learning based Recommender System: A Survey and New Perspectives
- A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
- Aspect-Aware Latent Factor Model: Rating Prediction with Ratings and Reviews
- MMALFM: Explainable Recommendation by Leveraging Reviews and Images
- Multi-Pointer Co-Attention Networks for Recommendation
- A Review-aware Graph Contrastive Learning Framework for Recommendation
- Attentive Aspect Modeling for Review-aware Recommendation
- User Diverse Preference Modeling by Multimodal Attentive Metric Learning
- News Session-Based Recommendations using Deep Neural Networks
- How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements
- Knowledge-Enhanced Personalized Review Generation with Capsule Graph Neural Network
- Review-Based Domain Disentanglement without Duplicate Users or Contexts for Cross-Domain Recommendation
- TransRev: Modeling Reviews as Translations from Users to Items
- Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text
- Towards a Near Universal Time Series Data Mining Tool: Introducing the Matrix Profile
- A Context-Aware User-Item Representation Learning for Item Recommendation
- A Review-Driven Neural Model for Sequential Recommendation
- A Capsule Network for Recommendation and Explaining What You Like and Dislike
- Understanding the Effectiveness of Reviews in E-commerce Top-N Recommendation
- A Zero Attentive Relevance Matching Networkfor Review Modeling in Recommendation System
- Recurrent Point Processes for Dynamic Review Models
- Self-Attentive Neural Collaborative Filtering
- Learning to Transfer Graph Embeddings for Inductive Graph based Recommendation
- LCMR: Local and Centralized Memories for Collaborative Filtering with Unstructured Text
- Recurrent Point Review Models
- AspeRa: Aspect-based Rating Prediction Model
- Assessing the Helpfulness of Review Content for Explaining Recommendations
- Augmenting the User-Item Graph with Textual Similarity Models
- Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation
- Asymmetrical Hierarchical Networks with Attentive Interactions for Interpretable Review-Based Recommendation
- TADO: Time-varying Attention with Dual-Optimizer Model
- Representation Learning by Reconstructing Neighborhoods
- Convolutional Quantum-Like Language Model with Mutual-Attention for Product Rating Prediction
- Personalized Neural Embeddings for Collaborative Filtering with Text
- Hybrid Deep Embedding for Recommendations with Dynamic Aspect-Level Explanations
- Hierarchical Text Interaction for Rating Prediction