Recurrent Neural Networks with Top-k Gains for Session-based Recommendations

Abstract

RNNs have been shown to be excellent models for sequential data and in particular for data that is generated by users in an session-based manner. The use of RNNs provides impressive performance benefits over classical methods in session-based recommendations. In this work we introduce novel ranking loss functions tailored to RNNs in the recommendation setting. The improved performance of these losses over alternatives, along with further tricks and refinements described in this work, allow for an overall improvement of up to 35% in terms of MRR and Recall@20 over previous session-based RNN solutions and up to 53% over classical collaborative filtering approaches. Unlike data augmentation-based improvements, our method does not increase training times significantly. We further demonstrate the performance gain of the RNN over baselines in an online A/B test.

CIKM'18, authors' version

References in corpus (4)

• BPR: Bayesian Personalized Ranking from Implicit Feedback
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Collaborative Filtering with Recurrent Neural Networks
• Recurrent Latent Variable Networks for Session-Based Recommendation

Cited by in corpus (145)

• Deep Learning based Recommender System: A Survey and New Perspectives
• Evaluation of Session-based Recommendation Algorithms
• Rethinking the Item Order in Session-based Recommendation with Graph Neural Networks
• Embarrassingly Shallow Autoencoders for Sparse Data
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
• Debiased Contrastive Learning for Sequential Recommendation
• Empirical Analysis of Session-Based Recommendation Algorithms
• Exploiting Cross-Session Information for Session-based Recommendation with Graph Neural Networks
• Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
• Incorporating User Micro-behaviors and Item Knowledge into Multi-task Learning for Session-based Recommendation
• Personalized Graph Neural Networks with Attention Mechanism for Session-Aware Recommendation
• Contextual Hybrid Session-based News Recommendation with Recurrent Neural Networks
• Session-based Recommendation with Hypergraph Attention Networks
• News Session-Based Recommendations using Deep Neural Networks
• CARCA: Context and Attribute-Aware Next-Item Recommendation via Cross-Attention
• Adversarial Sampling and Training for Semi-Supervised Information Retrieval
• Self-Attentive Sequential Recommendation
• A Survey on Session-based Recommender Systems
• Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations
• Price DOES Matter! Modeling Price and Interest Preferences in Session-based Recommendation
• RecGURU: Adversarial Learning of Generalized User Representations for Cross-Domain Recommendation
• MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation
• A Case Study on Sampling Strategies for Evaluating Neural Sequential Item Recommendation Models
• AutoMLP: Automated MLP for Sequential Recommendations
• Meta-optimized Contrastive Learning for Sequential Recommendation
• Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?
• FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddings
• DAN-SNR: A Deep Attentive Network for Social-Aware Next Point-of-Interest Recommendation
• Exploiting Positional Information for Session-based Recommendation
• Large Language Models for Intent-Driven Session Recommendations
• Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation
• Diffusion-based Contrastive Learning for Sequential Recommendation
• Diversification in Session-based News Recommender Systems
• Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
• Multi-intent-aware Session-based Recommendation
• Contrastive Multi-Level Graph Neural Networks for Session-based Recommendation
• MELT: Mutual Enhancement of Long-Tailed User and Item for Sequential Recommendation
• Modeling Users' Contextualized Page-wise Feedback for Click-Through Rate Prediction in E-commerce Search
• Widespread Flaws in Offline Evaluation of Recommender Systems
• Session-aware Linear Item-Item Models for Session-based Recommendation
• StackRec: Efficient Training of Very Deep Sequential Recommender Models by Iterative Stacking
• S-Walk: Accurate and Scalable Session-based Recommendationwith Random Walks
• M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations
• Understanding Diversity in Session-Based Recommendation
• Scaling Session-Based Transformer Recommendations using Optimized Negative Sampling and Loss Functions
• The Effect of Third Party Implementations on Reproducibility
• Counterfactual Collaborative Reasoning
• Masked and Swapped Sequence Modeling for Next Novel Basket Recommendation in Grocery Shopping
• BLOB : A Probabilistic Model for Recommendation that Combines Organic and Bandit Signals
• RepeatNet: A Repeat Aware Neural Recommendation Machine for Session-based Recommendation
• Self-Supervised Reinforcement Learning for Recommender Systems
• Revisiting BPR: A Replicability Study of a Common Recommender System Baseline
• CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network
• Long-Tail Session-based Recommendation from Calibration
• On the Effectiveness of Unlearning in Session-Based Recommendation
• Sequential recommendation with metric models based on frequent sequences
• Disentangling Past-Future Modeling in Sequential Recommendation via Dual Networks
• Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs
• Integrating Item Relevance in Training Loss for Sequential Recommender Systems
• RecJPQ: Training Large-Catalogue Sequential Recommenders
• Sequential Scenario-Specific Meta Learner for Online Recommendation
• Collaborative Filtering via High-Dimensional Regression
• DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games
• Personalized Purchase Prediction of Market Baskets with Wasserstein-Based Sequence Matching
• HAM: Hybrid Associations Models for Sequential Recommendation
• PARSRec: Explainable Personalized Attention-fused Recurrent Sequential Recommendation Using Session Partial Actions
• Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
• Self-Supervised Graph Co-Training for Session-based Recommendation
• RetaGNN: Relational Temporal Attentive Graph Neural Networks for Holistic Sequential Recommendation
• Joint Neural Collaborative Filtering for Recommender Systems
• Batch-Constrained Distributional Reinforcement Learning for Session-based Recommendation
• Learning Recommendations from User Actions in the Item-poor Insurance Domain
• Implicit Session Contexts for Next-Item Recommendations
• Context Tree for Adaptive Session-based Recommendation
• Dynamic Memory based Attention Network for Sequential Recommendation
• Graph Based Long-Term And Short-Term Interest Model for Click-Through Rate Prediction
• RECE: Reduced Cross-Entropy Loss for Large-Catalogue Sequential Recommenders
• MUSE: Music Recommender System with Shuffle Play Recommendation Enhancement
• Data-Driven Interaction Review of an Ed-Tech Application
• Sequential Recommendation in Online Games with Multiple Sequences, Tasks and User Levels
• Inter-sequence Enhanced Framework for Personalized Sequential Recommendation
• Session-Based Recommendation by Exploiting Substitutable and Complementary Relationships from Multi-behavior Data
• New Item Consumption Prediction Using Deep Learning
• Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation
• Calibration-Disentangled Learning and Relevance-Prioritized Reranking for Calibrated Sequential Recommendation
• Rethinking Lifelong Sequential Recommendation with Incremental Multi-Interest Attention
• M2: Mixed Models with Preferences, Popularities and Transitions for Next-Basket Recommendation
• Hierarchical Gating Networks for Sequential Recommendation
• Multi-Interest-Aware User Modeling for Large-Scale Sequential Recommendations
• A Simple Convolutional Generative Network for Next Item Recommendation
• Session-based Complementary Fashion Recommendations
• User-specific Adaptive Fine-tuning for Cross-domain Recommendations
• Memory Augmented Neural Model for Incremental Session-based Recommendation
• Deep Dynamic Neural Network to trade-off between Accuracy and Diversity in a News Recommender System
• Modeling Online Behavior in Recommender Systems: The Importance of Temporal Context
• Linear Item-Item Model with Neural Knowledge for Session-based Recommendation
• Modeling Spatial Trajectories using Coarse-Grained Smartphone Logs
• Sequential Learning over Implicit Feedback for Robust Large-Scale Recommender Systems
• ADER: Adaptively Distilled Exemplar Replay Towards Continual Learning for Session-based Recommendation
• General-Purpose User Embeddings based on Mobile App Usage
• Towards Amortized Ranking-Critical Training for Collaborative Filtering
• Temporal Collaborative Ranking Via Personalized Transformer
• Sequential Movie Genre Prediction using Average Transition Probability with Clustering
• Pareto Front Approximation for Multi-Objective Session-Based Recommender Systems
• Knowledge Transfer via Pre-training for Recommendation: A Review and Prospect
• Retrieval-Oriented Knowledge for Click-Through Rate Prediction
• Recommending Target Actions Outside Sessions in the Data-poor Insurance Domain
• Understanding or Manipulation: Rethinking Online Performance Gains of Modern Recommender Systems
• Improving Next-Application Prediction with Deep Personalized-Attention Neural Network
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Future-Aware Diverse Trends Framework for Recommendation
• Match4Rec: A Novel Recommendation Algorithm Based on Bidirectional Encoder Representation with the Matching Task
• Session-Based Recommender Systems for Action Selection in GUI Test Generation
• Latent Variable Session-Based Recommendation
• Path-Based Reasoning over Heterogeneous Networks for Recommendation via Bidirectional Modeling
• Memory Augmented Graph Neural Networks for Sequential Recommendation
• Advances in Collaborative Filtering and Ranking
• Hyperbolic Hypergraphs for Sequential Recommendation
• Context-Aware Drive-thru Recommendation Service at Fast Food Restaurants
• Temporal Meta-path Guided Explainable Recommendation
• CSRN: Collaborative Sequential Recommendation Networks for News Retrieval
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning
• Time-weighted Attentional Session-Aware Recommender System
• Matrix embedding method in match for session-based recommendation
• Scene-adaptive Knowledge Distillation for Sequential Recommendation via Differentiable Architecture Search
• TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations
• Reinforcement Learning based Path Exploration for Sequential Explainable Recommendation
• Retrieval & Interaction Machine for Tabular Data Prediction
• Next-item Recommendations in Short Sessions
• Hybrid Collaborative Filtering Models for Clinical Search Recommendation
• Searching Personal Collections
• Sequential Recommendation for Cold-start Users with Meta Transitional Learning
• CITIES: Contextual Inference of Tail-Item Embeddings for Sequential Recommendation
• Identifying Offline Metrics that Predict Online Impact: A Pragmatic Strategy for Real-World Recommender Systems
• SimDiffRec: Semantic Similarity-Guided Diffusion for Contrastive Sequential Recommendation
• RUEL: Retrieval-Augmented User Representation with Edge Browser Logs for Sequential Recommendation
• ragamAI: A Network Based Recommender System to Arrange a Indian Classical Music Concert
• Modeling and Analyzing the Influence of Non-Item Pages on Sequential Next-Item Prediction
• Modeling Multi-Destination Trips with Sketch-Based Model
• Sparse-Interest Network for Sequential Recommendation
• KATRec: Knowledge Aware aTtentive Sequential Recommendations
• MVIGER: Multi-View Variational Integration of Complementary Knowledge for Generative Recommender
• Improving Sequential Recommendation with Attribute-augmented Graph Neural Networks
• Adaptive Neural Architectures for Recommender Systems
• MBCAL: Sample Efficient and Variance Reduced Reinforcement Learning for Recommender Systems