Neural Collaborative Filtering
arXiv:1708.05031
Abstract
In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. However, the exploration of deep neural networks on recommender systems has received relatively less scrutiny. In this work, we strive to develop techniques based on neural networks to tackle the key problem in recommendation -- collaborative filtering -- on the basis of implicit feedback. Although some recent work has employed deep learning for recommendation, they primarily used it to model auxiliary information, such as textual descriptions of items and acoustic features of musics. When it comes to model the key factor in collaborative filtering -- the interaction between user and item features, they still resorted to matrix factorization and applied an inner product on the latent features of users and items. By replacing the inner product with a neural architecture that can learn an arbitrary function from data, we present a general framework named NCF, short for Neural network-based Collaborative Filtering. NCF is generic and can express and generalize matrix factorization under its framework. To supercharge NCF modelling with non-linearities, we propose to leverage a multi-layer perceptron to learn the user-item interaction function. Extensive experiments on two real-world datasets show significant improvements of our proposed NCF framework over the state-of-the-art methods. Empirical evidence shows that using deeper layers of neural networks offers better recommendation performance.
10 pages, 7 figures
References in corpus (4)
Cited by in corpus (58)
- NPA: Neural News Recommendation with Personalized Attention
- Neural Rating Regression with Abstractive Tips Generation for Recommendation
- Collaborative Memory Network for Recommendation Systems
- MMALFM: Explainable Recommendation by Leveraging Reviews and Images
- Poisoning Attacks to Graph-Based Recommender Systems
- Detecting drug-drug interactions using artificial neural networks and classic graph similarity measures
- Recommender Systems for Online and Mobile Social Networks: A survey
- Variational Autoencoders for Collaborative Filtering
- Cross-Market Product Recommendation
- The OARF Benchmark Suite: Characterization and Implications for Federated Learning Systems
- On Sampling Top-K Recommendation Evaluation
- Recommending Accurate and Diverse Items Using Bilateral Branch Network
- It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamic
- A Neural Influence Diffusion Model for Social Recommendation
- Signed Distance-based Deep Memory Recommender
- Neural Compatibility Modeling with Attentive Knowledge Distillation
- CnGAN: Generative Adversarial Networks for Cross-network user preference generation for non-overlapped users
- Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data
- Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System
- Point-of-Interest Recommendation: Exploiting Self-Attentive Autoencoders with Neighbor-Aware Influence
- A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information
- Cross-domain Recommendation via Deep Domain Adaptation
- Modeling Personalized Item Frequency Information for Next-basket Recommendation
- Image Matters: Visually modeling user behaviors using Advanced Model Server
- Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation
- MARS: Memory Attention-Aware Recommender System
- DeepReduce: A Sparse-tensor Communication Framework for Distributed Deep Learning
- Demystifying the MLPerf Benchmark Suite
- Recommendation Through Mixtures of Heterogeneous Item Relationships
- Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
- RecSSD: Near Data Processing for Solid State Drive Based Recommendation Inference
- Feature Interaction-aware Graph Neural Networks
- Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement
- Latent User Linking for Collaborative Cross Domain Recommendation
- Self-Attentive Neural Collaborative Filtering
- Interactive Recommender System via Knowledge Graph-enhanced Reinforcement Learning
- User Acceptance of Gender Stereotypes in Automated Career Recommendations
- Enabling the Analysis of Personality Aspects in Recommender Systems
- Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System
- Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View
- Sheaf4Rec: Sheaf Neural Networks for Graph-based Recommender Systems
- Social Influence-based Attentive Mavens Mining and Aggregative Representation Learning for Group Recommendation
- MRIF: Multi-resolution Interest Fusion for Recommendation
- Open Knowledge Enrichment for Long-tail Entities
- SceneRec: Scene-Based Graph Neural Networks for Recommender Systems
- Deep Item-based Collaborative Filtering for Top-N Recommendation
- Attribute-aware Collaborative Filtering: Survey and Classification
- Efficient Data-specific Model Search for Collaborative Filtering
- A Semi-Personalized System for User Cold Start Recommendation on Music Streaming Apps
- PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion
- UGRec: Modeling Directed and Undirected Relations for Recommendation
- Matrix Engines for High Performance Computing:A Paragon of Performance or Grasping at Straws?
- Gated Attentive-Autoencoder for Content-Aware Recommendation
- Sequential Variational Autoencoders for Collaborative Filtering
- FinBrain: When Finance Meets AI 2.0
- Neural Collaborative Ranking
- Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation
- Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation