Session-based Recommendations with Recurrent Neural Networks

Abstract

We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be provided. We therefore propose an RNN-based approach for session-based recommendations. Our approach also considers practical aspects of the task and introduces several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem. Experimental results on two data-sets show marked improvements over widely used approaches.

Camera ready version (17th February, 2016) Affiliation update (29th March, 2016)

References in corpus (1)

• BPR: Bayesian Personalized Ranking from Implicit Feedback

Cited by in corpus (139)

• Session-based Recommendation with Graph Neural Networks
• Personalizing Session-based Recommendations with Hierarchical Recurrent Neural Networks
• Deep Reinforcement Learning for Page-wise Recommendations
• Recommendations with Negative Feedback via Pairwise Deep Reinforcement Learning
• STAN: Spatio-Temporal Attention Network for Next Location Recommendation
• Embarrassingly Shallow Autoencoders for Sparse Data
• Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors
• Exploiting Cognitive Structure for Adaptive Learning
• R-Transformer: Recurrent Neural Network Enhanced Transformer
• M2GRL: A Multi-task Multi-view Graph Representation Learning Framework for Web-scale Recommender Systems
• Contrastive Self-supervised Sequential Recommendation with Robust Augmentation
• Session-aware Information Embedding for E-commerce Product Recommendation
• Collaborative Recurrent Autoencoder: Recommend while Learning to Fill in the Blanks
• Jointly Learning to Recommend and Advertise
• RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation
• Sequential/Session-based Recommendations: Challenges, Approaches, Applications and Opportunities
• Improved Recurrent Neural Networks for Session-based Recommendations
• Variational Autoencoders for Collaborative Filtering
• Next Item Recommendation with Self-Attention
• Deep Session Interest Network for Click-Through Rate Prediction
• It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamic
• Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation
• Interact and Decide: Medley of Sub-Attention Networks for Effective Group Recommendation
• Diversification in Session-based News Recommender Systems
• Joint Optimization of Tree-based Index and Deep Model for Recommender Systems
• Predicting purchasing intent: Automatic Feature Learning using Recurrent Neural Networks
• Ripple Knowledge Graph Convolutional Networks For Recommendation Systems
• Signed Distance-based Deep Memory Recommender
• CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users
• Temporal Learning and Sequence Modeling for a Job Recommender System
• Perceive Your Users in Depth: Learning Universal User Representations from Multiple E-commerce Tasks
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations
• Reinforcement Learning to Optimize Long-term User Engagement in Recommender Systems
• MinimalRNN: Toward More Interpretable and Trainable Recurrent Neural Networks
• Memory-efficient Embedding for Recommendations
• Toward Simulating Environments in Reinforcement Learning Based Recommendations
• SDM: Sequential Deep Matching Model for Online Large-scale Recommender System
• End-to-End User Behavior Retrieval in Click-Through RatePrediction Model
• Self-Supervised Reinforcement Learning for Recommender Systems
• CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network
• NeuRec: On Nonlinear Transformation for Personalized Ranking
• Modelling customer online behaviours with neural networks: applications to conversion prediction and advertising retargeting
• One Person, One Model, One World: Learning Continual User Representation without Forgetting
• Boosting Item-based Collaborative Filtering via Nearly Uncoupled Random Walks
• Balancing Multi-level Interactions for Session-based Recommendation
• Zero-Shot Recommender Systems
• Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations
• HAM: Hybrid Associations Models for Sequential Recommendation
• Top-K Off-Policy Correction for a REINFORCE Recommender System
• Interacting Attention-gated Recurrent Networks for Recommendation
• Modeling Personalized Item Frequency Information for Next-basket Recommendation
• Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
• Time is of the Essence: a Joint Hierarchical RNN and Point Process Model for Time and Item Predictions
• Personalized Embedding-based e-Commerce Recommendations at eBay
• Self-Supervised Graph Co-Training for Session-based Recommendation
• Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation
• A Generic Network Compression Framework for Sequential Recommender Systems
• Energy-Based Sequence GANs for Recommendation and Their Connection to Imitation Learning
• DGTN: Dual-channel Graph Transition Network for Session-based Recommendation
• Dynamic Knowledge embedding and tracing
• Modelling Sequential Music Track Skips using a Multi-RNN Approach
• Dynamic Memory based Attention Network for Sequential Recommendation
• Continuous-Time Sequential Recommendation with Temporal Graph Collaborative Transformer
• DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation
• DeepRec: An Open-source Toolkit for Deep Learning based Recommendation
• Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
• An Adjustable Heat Conduction based KNN Approach for Session-based Recommendation
• Sequential Recommendation with Relation-Aware Kernelized Self-Attention
• CAPS: Context Aware Personalized POI Sequence Recommender System
• New Item Consumption Prediction Using Deep Learning
• Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation
• Getting deep recommenders fit: Bloom embeddings for sparse binary input/output networks
• HCGR: Hyperbolic Contrastive Graph Representation Learning for Session-based Recommendation
• Towards Off-Policy Reinforcement Learning for Ranking Policies with Human Feedback
• Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding
• Imitation-Regularized Offline Learning
• Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
• DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation
• Pre-training Graph Transformer with Multimodal Side Information for Recommendation
• Deep inference of latent dynamics with spatio-temporal super-resolution using selective backpropagation through time
• ShadowTutor: Distributed Partial Distillation for Mobile Video DNN Inference
• Mixture-of-tastes Models for Representing Users with Diverse Interests
• Attention-based Mixture Density Recurrent Networks for History-based Recommendation
• JSCN: Joint Spectral Convolutional Network for Cross Domain Recommendation
• Neighborhood-Enhanced and Time-Aware Model for Session-based Recommendation
• Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation
• Multi-Interest-Aware User Modeling for Large-Scale Sequential Recommendations
• A Simple Convolutional Generative Network for Next Item Recommendation
• Learning to Structure Long-term Dependence for Sequential Recommendation
• Correcting the User Feedback-Loop Bias for Recommendation Systems
• MV-RNN: A Multi-View Recurrent Neural Network for Sequential Recommendation
• Sequential Movie Genre Prediction using Average Transition Probability with Clustering
• Self-Attentive Neural Collaborative Filtering
• Temporal Collaborative Ranking Via Personalized Transformer
• Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System
• Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
• Towards Content Provider Aware Recommender Systems: A Simulation Study on the Interplay between User and Provider Utilities
• Multi-behavior Graph Contextual Aware Network for Session-based Recommendation
• Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective
• Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View
• Quaternion Collaborative Filtering for Recommendation
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Future-Aware Diverse Trends Framework for Recommendation
• Hyperbolic Hypergraphs for Sequential Recommendation
• Many-to-one Recurrent Neural Network for Session-based Recommendation
• Temporal Meta-path Guided Explainable Recommendation
• Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution
• Advances in Collaborative Filtering and Ranking
• Deep Reinforcement Learning for Personalized Search Story Recommendation
• NAIRS: A Neural Attentive Interpretable Recommendation System
• Deep Hierarchical Reinforcement Learning Based Recommendations via Multi-goals Abstraction
• SeER: An Explainable Deep Learning MIDI-based Hybrid Song Recommender System
• Out-of-Town Recommendation with Travel Intention Modeling
• Hybrid Collaborative Filtering Models for Clinical Search Recommendation
• Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
• InfoBehavior: Self-supervised Representation Learning for Ultra-long Behavior Sequence via Hierarchical Grouping
• Data Optimisation for a Deep Learning Recommender System
• Sequential Recommendation for Cold-start Users with Meta Transitional Learning
• KATRec: Knowledge Aware aTtentive Sequential Recommendations
• Cross-Batch Negative Sampling for Training Two-Tower Recommenders
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning
• Differentially Private Neighborhood-based Recommender Systems
• Representation Extraction and Deep Neural Recommendation for Collaborative Filtering
• Session-based k-NNs with Semantic Suggestions for Next-item Prediction
• $C^{3}DRec$: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Era
• Sparse-Interest Network for Sequential Recommendation
• Improving Sequential Recommendation with Attribute-augmented Graph Neural Networks
• Large-scale Real-time Personalized Similar Product Recommendations
• Attentive Long Short-Term Preference Modeling for Personalized Product Search
• Linked Recurrent Neural Networks
• Binary Latent Representations for Efficient Ranking: Empirical Assessment
• Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation
• Consistency-Aware Recommendation for User-Generated ItemList Continuation
• Goal-based Course Recommendation
• Causal Embeddings for Recommendation: An Extended Abstract
• Coupled Variational Recurrent Collaborative Filtering
• Preliminary Evaluation of the Test-Time Training Layers in Recommendation System (Student Abstract)