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 (3)

• Joint Deep Modeling of Users and Items Using Reviews for Recommendation
• A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data
• Deep Learning over Multi-field Categorical Data: A Case Study on User Response Prediction

Cited by in corpus (168)

• Deep Learning based Recommender System: A Survey and New Perspectives
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• Deep Neural Networks and Tabular Data: A Survey
• Deep Learning Recommendation Model for Personalization and Recommendation Systems
• NPA: Neural News Recommendation with Personalized Attention
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
• Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors
• 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
• Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems
• $F{M}^2$: Field-matrixed Factorization Machines for Recommender Systems
• Deep Reinforcement Learning based Recommendation with Explicit User-Item Interactions Modeling
• SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
• Jointly Learning to Recommend and Advertise
• HET: Scaling out Huge Embedding Model Training via Cache-enabled Distributed Framework
• Predicting Yield Performance of Parents in Plant Breeding: A Neural Collaborative Filtering Approach
• Causality-based CTR Prediction using Graph Neural Networks
• Deep Session Interest Network for Click-Through Rate Prediction
• Deep Interest Network for Click-Through Rate Prediction
• Predicting Different Types of Conversions with Multi-Task Learning in Online Advertising
• Neural News Recommendation with Attentive Multi-View Learning
• DeepFM: An End-to-End Wide & Deep Learning Framework for CTR Prediction
• A Neural Influence Diffusion Model for Social Recommendation
• Mixed Dimension Embeddings with Application to Memory-Efficient Recommendation Systems
• Information Theoretic Counterfactual Learning from Missing-Not-At-Random Feedback
• Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems
• Disentangled Self-Attentive Neural Networks for Click-Through Rate Prediction
• Evolving Context-Aware Recommender Systems With Users in Mind
• 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
• Product-based Neural Networks for User Response Prediction over Multi-field Categorical Data
• Deep Position-wise Interaction Network for CTR Prediction
• AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations
• DeepCF: A Unified Framework of Representation Learning and Matching Function Learning in Recommender System
• Learning from Multi-View Multi-Way Data via Structural Factorization Machines
• Learnable Embedding Sizes for Recommender Systems
• MaskNet: Introducing Feature-Wise Multiplication to CTR Ranking Models by Instance-Guided Mask
• FLEN: Leveraging Field for Scalable CTR Prediction
• GateNet: Gating-Enhanced Deep Network for Click-Through Rate Prediction
• End-to-End User Behavior Retrieval in Click-Through RatePrediction Model
• A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction
• Controllable Multi-Interest Framework for Recommendation
• Mixture of Virtual-Kernel Experts for Multi-Objective User Profile Modeling
• One Person, One Model, One World: Learning Continual User Representation without Forgetting
• Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
• 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
• MM-Rec: Multimodal News Recommendation
• Hijack Vertical Federated Learning Models As One Party
• Parameter-Efficient Transfer from Sequential Behaviors for User Modeling and Recommendation
• Entire Space Multi-Task Modeling via Post-Click Behavior Decomposition for Conversion Rate Prediction
• Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data
• DebiasedRec: Bias-aware User Modeling and Click Prediction for Personalized News Recommendation
• GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
• Image Matters: Visually modeling user behaviors using Advanced Model Server
• Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks
• Matching Algorithms: Fundamentals, Applications and Challenges
• Joint Neural Collaborative Filtering for Recommender Systems
• Dynamic Memory based Attention Network for Sequential Recommendation
• Edge-Cloud Collaboration Enabled Video Service Enhancement: A Hybrid Human-Artificial Intelligence Scheme
• Deep Learning for Click-Through Rate Estimation
• Privacy-Aware Recommender Systems Challenge on Twitter's Home Timeline
• An Adjustable Heat Conduction based KNN Approach for Session-based Recommendation
• Time-based Sequence Model for Personalization and Recommendation Systems
• Price-aware Recommendation with Graph Convolutional Networks
• DADNN: Multi-Scene CTR Prediction via Domain-Aware Deep Neural Network
• Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task
• MC${}^2$-SF: Slow-Fast Learning for Mobile-Cloud Collaborative Recommendation
• FedCTR: Federated Native Ad CTR Prediction with Multi-Platform User Behavior Data
• Training with Multi-Layer Embeddings for Model Reduction
• Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
• Graph Factorization Machines for Cross-Domain Recommendation
• 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
• Learning Effective Representations for Person-Job Fit by Feature Fusion
• CPR: Understanding and Improving Failure Tolerant Training for Deep Learning Recommendation with Partial Recovery
• ContextNet: A Click-Through Rate Prediction Framework Using Contextual information to Refine Feature Embedding
• Denoising User-aware Memory Network for Recommendation
• Practical Privacy Preserving POI Recommendation
• An Intelligent Group Event Recommendation System in Social networks
• DemiNet: Dependency-Aware Multi-Interest Network with Self-Supervised Graph Learning for Click-Through Rate Prediction
• Click-Through Rate Prediction Using Graph Neural Networks and Online Learning
• Multi-Interest-Aware User Modeling for Large-Scale Sequential Recommendations
• DNN2LR: Interpretation-inspired Feature Crossing for Real-world Tabular Data
• Adaptive Serverless Learning
• DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving
• MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection
• Feature Interaction-aware Graph Neural Networks
• Operation-aware Neural Networks for User Response Prediction
• Self-Attentive Neural Collaborative Filtering
• Res-embedding for Deep Learning Based Click-Through Rate Prediction Modeling
• Feature Interaction based Neural Network for Click-Through Rate Prediction
• Multi-Level Deep Cascade Trees for Conversion Rate Prediction in Recommendation System
• Multi-Graph Convolution Collaborative Filtering
• An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation
• An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
• Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations
• Iterative Boosting Deep Neural Networks for Predicting Click-Through Rate
• UBER-GNN: A User-Based Embeddings Recommendation based on Graph Neural Networks
• Distillation based Multi-task Learning: A Candidate Generation Model for Improving Reading Duration
• Random Offset Block Embedding Array (ROBE) for CriteoTB Benchmark MLPerf DLRM Model : 1000$\times$ Compression and 3.1$\times$ Faster Inference
• Enhancing Factorization Machines with Generalized Metric Learning
• Improving Conversational Recommendation System by Pretraining on Billions Scale of Knowledge Graph
• Scenario-aware and Mutual-based approach for Multi-scenario Recommendation in E-Commerce
• MISS: Multi-Interest Self-Supervised Learning Framework 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
• Dynamic Sequential Graph Learning for Click-Through Rate Prediction
• Explainable Recommendation Systems by Generalized Additive Models with Manifest and Latent Interactions
• Implicit Feedback Deep Collaborative Filtering Product Recommendation System
• AutoRec: An Automated Recommender System
• Explainable Student Performance Prediction With Personalized Attention for Explaining Why A Student Fails
• Scaling Law for Recommendation Models: Towards General-purpose User Representations
• PURS: Personalized Unexpected Recommender System for Improving User Satisfaction
• Learning Effective and Efficient Embedding via an Adaptively-Masked Twins-based Layer
• Toward a benchmark for CTR prediction in online advertising: datasets, evaluation protocols and perspectives
• Multimodal Topic Learning for Video Recommendation
• Multi-Interactive Attention Network for Fine-grained Feature Learning in CTR Prediction
• GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs
• BCFNet: A Balanced Collaborative Filtering Network with Attention Mechanism
• Personalized Adaptive Meta Learning for Cold-start User Preference Prediction
• Sequence-Aware Factorization Machines for Temporal Predictive Analytics
• Recommendation with Attribute-aware Product Networks: A Representation Learning Model
• Deep Time-Stream Framework for Click-Through Rate Prediction by Tracking Interest Evolution
• Privileged Features Distillation at Taobao Recommendations
• Attribute-aware Collaborative Filtering: Survey and Classification
• Leaf-FM: A Learnable Feature Generation Factorization Machine for Click-Through Rate Prediction
• An Educational System for Personalized Teacher Recommendation in K-12 Online Classrooms
• Towards Scheduling Federated Deep Learning using Meta-Gradients for Inter-Hospital Learning
• Efficient Click-Through Rate Prediction for Developing Countries via Tabular Learning
• On the Fairness of Randomized Trials for Recommendation with Heterogeneous Demographics and Beyond
• $C^{3}DRec$: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Era
• TrNews: Heterogeneous User-Interest Transfer Learning for News Recommendation
• Adaptively Weighted Top-N Recommendation for Organ Matching
• Cross-Modal Alignment with Mixture Experts Neural Network for Intral-City Retail Recommendation
• Large-scale Causal Approaches to Debiasing Post-click Conversion Rate Estimation with Multi-task Learning
• CPM-sensitive AUC for CTR prediction
• Sparse-Interest Network for Sequential Recommendation
• Spectrum Attention Mechanism for Time Series Classification
• Dual Attentive Sequential Learning for Cross-Domain Click-Through Rate Prediction
• Chromatic Learning for Sparse Datasets
• Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits
• A Recommendation System to Enhance Midwives' Capacities in Low-Income Countries
• Search-Based Serving Architecture of Embeddings-Based Recommendations
• Explicit Semantic Cross Feature Learning via Pre-trained Graph Neural Networks for CTR Prediction
• SHORING: Design Provable Conditional High-Order Interaction Network via Symbolic Testing
• Gated Attentive-Autoencoder for Content-Aware Recommendation
• Online Interaction Detection for Click-Through Rate Prediction
• Collaborative Similarity Embedding for Recommender Systems
• FinBrain: When Finance Meets AI 2.0
• Session-aware Item-combination Recommendation with Transformer Network
• Memory-Efficient Factorization Machines via Binarizing both Data and Model Coefficients
• DGEM: A New Dual-modal Graph Embedding Method in Recommendation System
• Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling
• AdnFM: An Attentive DenseNet based Factorization Machine for CTR Prediction
• Broad Learning for Healthcare
• Dynamic Parameterized Network for CTR Prediction
• Breaking the Softmax Bottleneck for Sequential Recommender Systems with Dropout and Decoupling
• Field-aware Neural Factorization Machine for Click-Through Rate Prediction
• An Efficient Agreement Mechanism in CapsNets By Pairwise Product
• DS-FACTO: Doubly Separable Factorization Machines
• On the Effectiveness of Low-rank Approximations for Collaborative Filtering compared to Neural Networks
• Neural News Recommendation with Negative Feedback