Translation-based Recommendation

Abstract

Modeling the complex interactions between users and items as well as amongst items themselves is at the core of designing successful recommender systems. One classical setting is predicting users' personalized sequential behavior (or `next-item' recommendation), where the challenges mainly lie in modeling `third-order' interactions between a user, her previously visited item(s), and the next item to consume. Existing methods typically decompose these higher-order interactions into a combination of pairwise relationships, by way of which user preferences (user-item interactions) and sequential patterns (item-item interactions) are captured by separate components. In this paper, we propose a unified method, TransRec, to model such third-order relationships for large-scale sequential prediction. Methodologically, we embed items into a `transition space' where users are modeled as translation vectors operating on item sequences. Empirically, this approach outperforms the state-of-the-art on a wide spectrum of real-world datasets. Data and code are available at https://sites.google.com/a/eng.ucsd.edu/ruining-he/.

9 pages, 5 figures

References in corpus (3)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Complex Embeddings for Simple Link Prediction
• Learning Compatibility Across Categories for Heterogeneous Item Recommendation

Cited by in corpus (83)

• Unifying Knowledge Graph Learning and Recommendation: Towards a Better Understanding of User Preferences
• Learning over Knowledge-Base Embeddings for Recommendation
• Learning Heterogeneous Knowledge Base Embeddings for Explainable Recommendation
• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
• FairRec: Two-Sided Fairness for Personalized Recommendations in Two-Sided Platforms
• Lightweight Self-Attentive Sequential Recommendation
• Contrastive Cross-Domain Sequential Recommendation
• Session-based Recommendation with Hypergraph Attention Networks
• Neural Collaborative Reasoning
• Self-Attentive Sequential Recommendation
• RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation
• Time-aware Path Reasoning on Knowledge Graph for Recommendation
• Transfer Learning via Contextual Invariants for One-to-Many Cross-Domain Recommendation
• MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation
• AdaMCT: Adaptive Mixture of CNN-Transformer for Sequential Recommendation
• Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?
• Next Item Recommendation with Self-Attention
• Recommender systems based on graph embedding techniques: A comprehensive review
• Hierarchical Transformer with Spatio-Temporal Context Aggregation for Next Point-of-Interest Recommendation
• Recommending Accurate and Diverse Items Using Bilateral Branch Network
• Towards Fair Recommendation in Two-Sided Platforms
• RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms
• Signed Distance-based Deep Memory Recommender
• Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluation
• Relational Collaborative Filtering:Modeling Multiple Item Relations for Recommendation
• TransRev: Modeling Reviews as Translations from Users to Items
• Controllable Multi-Interest Framework for Recommendation
• CT4Rec: Simple yet Effective Consistency Training for Sequential Recommendation
• On the Effectiveness of Unlearning in Session-Based Recommendation
• Sequential recommendation with metric models based on frequent sequences
• UPRec: User-Aware Pre-training for Recommender Systems
• Time to Split: Exploring Data Splitting Strategies for Offline Evaluation of Sequential Recommenders
• Recommending on graphs: a comprehensive review from a data perspective
• Relation Embedding for Personalised POI Recommendation
• Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis
• PARSRec: Explainable Personalized Attention-fused Recurrent Sequential Recommendation Using Session Partial Actions
• A Long-Short Demands-Aware Model for Next-Item Recommendation
• Collaboration and Transition: Distilling Item Transitions into Multi-Query Self-Attention for Sequential Recommendation
• Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network
• Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
• Analyzing Knowledge Graph Embedding Methods from a Multi-Embedding Interaction Perspective
• Vertical Allocation-based Fair Exposure Amortizing in Ranking
• Sequential Recommendation in Online Games with Multiple Sequences, Tasks and User Levels
• Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
• Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
• Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation
• Modeling Sequences as Distributions with Uncertainty for Sequential Recommendation
• Recommendation Through Mixtures of Heterogeneous Item Relationships
• Basket Recommendation with Multi-Intent Translation Graph Neural Network
• Hierarchical Gating Networks for Sequential Recommendation
• Edge-Enhanced Global Disentangled Graph Neural Network for Sequential Recommendation
• Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
• On the Value of Bandit Feedback for Offline Recommender System Evaluation
• Multi-Scale Quasi-RNN for Next Item Recommendation
• Sequeval: A Framework to Assess and Benchmark Sequence-based Recommender Systems
• Temporal Collaborative Ranking Via Personalized Transformer
• Learning to Embed Categorical Features without Embedding Tables for Recommendation
• X-Cross: Dynamic Integration of Language Models for Cross-Domain Sequential Recommendation
• Explore User Neighborhood for Real-time E-commerce Recommendation
• Fairness-aware Personalized Ranking Recommendation via Adversarial Learning
• Future-Aware Diverse Trends Framework for Recommendation
• Why should I not follow you? Reasons For and Reasons Against in Responsible Recommender Systems
• Memory Augmented Graph Neural Networks for Sequential Recommendation
• Augmenting the User-Item Graph with Textual Similarity Models
• Algorithmic Fairness Datasets: the Story so Far
• Advances in Collaborative Filtering and Ranking
• Enhancing Recommendation with Denoising Auxiliary Task
• Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems
• Multi-Facet Recommender Networks with Spherical Optimization
• Sequential Variational Autoencoders for Collaborative Filtering
• Learning User Representations with Hypercuboids for Recommender Systems
• Consistency-Aware Recommendation for User-Generated ItemList Continuation
• Retrieval & Interaction Machine for Tabular Data Prediction
• Collaborative Translational Metric Learning
• Skewness Ranking Optimization for Personalized Recommendation
• Sequential Recommendation for Cold-start Users with Meta Transitional Learning
• Addressing Class-Imbalance Problem in Personalized Ranking
• Cascading: Association Augmented Sequential Recommendation
• Cross-Domain Collaborative Filtering via Translation-based Learning
• TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations
• Probabilistic Metric Learning with Adaptive Margin for Top-K Recommendation