Collaborative Memory Network for Recommendation Systems

Abstract

Recommendation systems play a vital role to keep users engaged with personalized content in modern online platforms. Deep learning has revolutionized many research fields and there is a recent surge of interest in applying it to collaborative filtering (CF). However, existing methods compose deep learning architectures with the latent factor model ignoring a major class of CF models, neighborhood or memory-based approaches. We propose Collaborative Memory Networks (CMN), a deep architecture to unify the two classes of CF models capitalizing on the strengths of the global structure of latent factor model and local neighborhood-based structure in a nonlinear fashion. Motivated by the success of Memory Networks, we fuse a memory component and neural attention mechanism as the neighborhood component. The associative addressing scheme with the user and item memories in the memory module encodes complex user-item relations coupled with the neural attention mechanism to learn a user-item specific neighborhood. Finally, the output module jointly exploits the neighborhood with the user and item memories to produce the ranking score. Stacking multiple memory modules together yield deeper architectures capturing increasingly complex user-item relations. Furthermore, we show strong connections between CMN components, memory networks and the three classes of CF models. Comprehensive experimental results demonstrate the effectiveness of CMN on three public datasets outperforming competitive baselines. Qualitative visualization of the attention weights provide insight into the model's recommendation process and suggest the presence of higher order interactions.

arXiv commentPublished as ACM SIGIR 2018 Full Paper

References in corpus (8)

• Neural Machine Translation by Jointly Learning to Align and Translate
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Dynamic Memory Networks for Visual and Textual Question Answering
• IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
• Neural Collaborative Filtering
• AutoSVD++: An Efficient Hybrid Collaborative Filtering Model via Contractive Auto-encoders
• Deep Memory Networks for Attitude Identification

Cited by in corpus (64)

• Neural Graph Collaborative Filtering
• Disentangled Graph Collaborative Filtering
• Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Advances and Challenges in Conversational Recommender Systems: A Survey
• Estimation-Action-Reflection: Towards Deep Interaction Between Conversational and Recommender Systems
• Practice on Long Sequential User Behavior Modeling for Click-Through Rate Prediction
• A Troubling Analysis of Reproducibility and Progress in Recommender Systems Research
• Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
• Attentive Aspect Modeling for Review-aware Recommendation
• User Diverse Preference Modeling by Multimodal Attentive Metric Learning
• User Behavior Retrieval for Click-Through Rate Prediction
• Collaboration-Aware Graph Convolutional Network for Recommender Systems
• Quality Metrics in Recommender Systems: Do We Calculate Metrics Consistently?
• Topic-Enhanced Memory Networks for Personalised Point-of-Interest Recommendation
• Click-Through Rate Prediction with Multi-Modal Hypergraphs
• On Sampling Top-K Recommendation Evaluation
• Signed Distance-based Deep Memory Recommender
• DaisyRec 2.0: Benchmarking Recommendation for Rigorous Evaluation
• Robust Collaborative Filtering to Popularity Distribution Shift
• SimpleX: A Simple and Strong Baseline for Collaborative Filtering
• BHIN2vec: Balancing the Type of Relation in Heterogeneous Information Network
• User Consented Federated Recommender System Against Personalized Attribute Inference Attack
• CmnRec: Sequential Recommendations with Chunk-accelerated Memory Network
• Controllable Multi-Interest Framework for Recommendation
• Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
• Quaternion-Based Self-Attentive Long Short-Term User Preference Encoding for Recommendation
• DBRec: Dual-Bridging Recommendation via Discovering Latent Groups
• Evaluation Metrics for Item Recommendation under Sampling
• Learning to Respond with Your Favorite Stickers: A Framework of Unifying Multi-Modality and User Preference in Multi-Turn Dialog
• Transfer Meets Hybrid: A Synthetic Approach for Cross-Domain Collaborative Filtering with Text
• Graph Neural Pre-training for Enhancing Recommendations using Side Information
• ARGO: Modeling Heterogeneity in E-commerce Recommendation
• Creating Auxiliary Representations from Charge Definitions for Criminal Charge Prediction
• Collaborative Metric Learning with Memory Network for Multi-Relational Recommender Systems
• LT-OCF: Learnable-Time ODE-based Collaborative Filtering
• Candidate Set Sampling for Evaluating Top-N Recommendation
• Heterogeneous Graph Collaborative Filtering
• Graph Attention Collaborative Similarity Embedding for Recommender System
• Hyperbolic Neural Collaborative Recommender
• ICS-Assist: Intelligent Customer Inquiry Resolution Recommendation in Online Customer Service for Large E-Commerce Businesses
• Criterion-based Heterogeneous Collaborative Filtering for Multi-behavior Implicit Recommendation
• A Neural Attention Model for Adaptive Learning of Social Friends' Preferences
• Explore User Neighborhood for Real-time E-commerce Recommendation
• Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential Recommendation
• Maximizing Cumulative User Engagement in Sequential Recommendation: An Online Optimization Perspective
• On Estimating Recommendation Evaluation Metrics under Sampling
• A short note on the decision tree based neural turing machine
• SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
• Linear, or Non-Linear, That is the Question!
• How Powerful is Graph Convolution for Recommendation?
• Beyond Similarity: Relation Embedding with Dual Attentions for Item-based Recommendation
• Consistency-Aware Recommendation for User-Generated ItemList Continuation
• Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation
• Deep Learning-based Online Alternative Product Recommendations at Scale
• Hybrid Attentional Memory Network for Computational drug repositioning
• Personalized Neural Embeddings for Collaborative Filtering with Text
• Quaternion-Based Graph Convolution Network for Recommendation
• Fully Hyperbolic Graph Convolution Network for Recommendation
• Adaptive Neural Architectures for Recommender Systems
• A Unified Model for Recommendation with Selective Neighborhood Modeling
• Explainable Recommendations via Attentive Multi-Persona Collaborative Filtering
• Collaborative Filtering Through Weighted Similarities of User and Item Embeddings
• Sequential Recommender via Time-aware Attentive Memory Network