Deep & Cross Network for Ad Click Predictions

Abstract

Feature engineering has been the key to the success of many prediction models. However, the process is non-trivial and often requires manual feature engineering or exhaustive searching. DNNs are able to automatically learn feature interactions; however, they generate all the interactions implicitly, and are not necessarily efficient in learning all types of cross features. In this paper, we propose the Deep & Cross Network (DCN) which keeps the benefits of a DNN model, and beyond that, it introduces a novel cross network that is more efficient in learning certain bounded-degree feature interactions. In particular, DCN explicitly applies feature crossing at each layer, requires no manual feature engineering, and adds negligible extra complexity to the DNN model. Our experimental results have demonstrated its superiority over the state-of-art algorithms on the CTR prediction dataset and dense classification dataset, in terms of both model accuracy and memory usage.

In Proceedings of AdKDD and TargetAd, Halifax, NS, Canada, August, 14, 2017, 7 pages

References in corpus (1)

• Wide & Deep Learning for Recommender Systems

Cited by in corpus (20)

• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• Federated Meta-Learning with Fast Convergence and Efficient Communication
• $F{M}^2$: Field-matrixed Factorization Machines for Recommender Systems
• Deep Metric Learning-based Image Retrieval System for Chest Radiograph and its Clinical Applications in COVID-19
• Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
• Bandana: Using Non-volatile Memory for Storing Deep Learning Models
• Learning from Multi-View Multi-Way Data via Structural Factorization Machines
• Memory-efficient Embedding for Recommendations
• A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction
• Modelling customer online behaviours with neural networks: applications to conversion prediction and advertising retargeting
• Large-scale Collaborative Filtering with Product Embeddings
• AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications
• Efficient Inner Product Approximation in Hybrid Spaces
• Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction
• Operation-aware Neural Networks for User Response Prediction
• Denoising User-aware Memory Network for Recommendation
• DeepLight: Deep Lightweight Feature Interactions for Accelerating CTR Predictions in Ad Serving
• Privileged Features Distillation at Taobao Recommendations
• Multimodal Topic Learning for Video Recommendation
• Adversarial Mixture Of Experts with Category Hierarchy Soft Constraint