DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Abstract

Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods seem to have a strong bias towards low- or high-order interactions, or require expertise feature engineering. In this paper, we show that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions. The proposed model, DeepFM, combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture. Compared to the latest Wide \& Deep model from Google, DeepFM has a shared input to its "wide" and "deep" parts, with no need of feature engineering besides raw features. Comprehensive experiments are conducted to demonstrate the effectiveness and efficiency of DeepFM over the existing models for CTR prediction, on both benchmark data and commercial data.

References in corpus (1)

• Joint Deep Modeling of Users and Items Using Reviews for Recommendation

Cited by in corpus (99)

• Deep Learning Recommendation Model for Personalization and Recommendation Systems
• NPA: Neural News Recommendation with Personalized Attention
• DKN: Deep Knowledge-Aware Network for News Recommendation
• DGCN: Diversified Recommendation with Graph Convolutional Networks
• Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction
• $F{M}^2$: Field-matrixed Factorization Machines for Recommender Systems
• SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
• HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework
• Deep Session Interest Network for Click-Through Rate Prediction
• Neural News Recommendation with Attentive Multi-View Learning
• A Neural Influence Diffusion Model for Social Recommendation
• Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
• Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation
• TFNet: Multi-Semantic Feature Interaction for CTR Prediction
• Hierarchical Temporal Convolutional Networks for Dynamic Recommender Systems
• Deep Position-wise Interaction Network for CTR Prediction
• DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System
• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations
• Learnable Embedding Sizes for Recommender Systems
• A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction
• End-to-End User Behavior Retrieval in Click-Through RatePrediction Model
• GateNet: Gating-Enhanced Deep Network for Click-Through Rate Prediction
• Controllable Multi-Interest Framework for Recommendation
• UPRec: User-Aware Pre-training for Recommender Systems
• FAT-DeepFFM: Field Attentive Deep Field-aware Factorization Machine
• An Incremental Learning framework for Large-scale CTR Prediction
• Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data
• Joint Neural Collaborative Filtering for Recommender Systems
• GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
• DebiasedRec: Bias-aware User Modeling and Click Prediction for Personalized News Recommendation
• Matching Algorithms: Fundamentals, Applications and Challenges
• Deep Learning for Click-Through Rate Estimation
• Edge-Cloud Collaboration Enabled Video Service Enhancement: A Hybrid Human-Artificial Intelligence Scheme
• Dynamic Memory based Attention Network for Sequential Recommendation
• DADNN: Multi-Scene CTR Prediction via Domain-Aware Deep Neural Network
• MC${}^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation
• Time-based Sequence Model for Personalization and Recommendation Systems
• Empowering News Recommendation with Pre-trained Language Models
• Correct Normalization Matters: Understanding the Effect of Normalization On Deep Neural Network Models For Click-Through Rate Prediction
• Pairwise Interactive Graph Attention Network for Context-Aware Recommendation
• FedCTR: Federated Native Ad CTR Prediction with Multi-Platform User Behavior Data
• Graph Factorization Machines for Cross-Domain Recommendation
• Training with Multi-Layer Embeddings for Model Reduction
• Denoising User-aware Memory Network for Recommendation
• An Intelligent Group Event Recommendation System in Social networks
• Adaptive Serverless Learning
• Learning Effective Representations for Person-Job Fit by Feature Fusion
• Practical Privacy Preserving POI Recommendation
• ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding
• CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery
• Operation-aware Neural Networks for User Response Prediction
• Iterative Boosting Deep Neural Networks for Predicting Click-Through Rate
• Multi-Graph Convolution Collaborative Filtering
• An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
• Res-embedding for Deep Learning Based Click-Through Rate Prediction Modeling
• Feature Interaction based Neural Network for Click-Through Rate Prediction
• Explainable Student Performance Prediction With Personalized Attention for Explaining Why A Student Fails
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Prediction
• TPG-DNN: A Method for User Intent Prediction Based on Total Probability Formula and GRU Loss with Multi-task Learning
• Distillation based Multi-task Learning: A Candidate Generation Model for Improving Reading Duration
• UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks
• Scenario-aware and Mutual-based approach for Multi-scenario Recommendation in E-Commerce
• Explainable Recommendation Systems by Generalized Additive Models with Manifest and Latent Interactions
• AutoRec: An Automated Recommender System
• Leaf-FM: A Learnable Feature Generation Factorization Machine for Click-Through Rate Prediction
• Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
• Towards Scheduling Federated Deep Learning using Meta-Gradients for Inter-Hospital Learning
• An Educational System for Personalized Teacher Recommendation in K-12 Online Classrooms
• GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs
• Multimodal Topic Learning for Video Recommendation
• Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• Sequence-Aware Factorization Machines for Temporal Predictive Analytics
• BCFNet: A Balanced Collaborative Filtering Network with Attention Mechanism
• Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
• Online Interaction Detection for Click-Through Rate Prediction
• Chromatic Learning for Sparse Datasets
• On the Effectiveness of Low-rank Approximations for Collaborative Filtering compared to Neural Networks
• DS-FACTO: Doubly Separable Factorization Machines
• Spectrum Attention Mechanism for Time Series Classification
• Efficient Click-Through Rate Prediction for Developing Countries via Tabular Learning
• Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling
• Search-Based Serving Architecture of Embeddings-Based Recommendations
• Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation
• Sparse-Interest Network for Sequential Recommendation
• TrNews: Heterogeneous User-Interest Transfer Learning for News Recommendation
• $C^{3}DRec$: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Era
• Neural News Recommendation with Negative Feedback
• Dynamic Parameterized Network for CTR Prediction
• Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling
• Memory-Efficient Factorization Machines via Binarizing both Data and Model Coefficients
• Collaborative Similarity Embedding for Recommender Systems
• Field-aware Neural Factorization Machine for Click-Through Rate Prediction
• DGEM: A New Dual-modal Graph Embedding Method in Recommendation System
• SHORING: Design Provable Conditional High-Order Interaction Network via Symbolic Testing
• Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
• CPM-sensitive AUC for CTR prediction
• Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction