A General Method For Automatic Discovery of Powerful Interactions In Click-Through Rate Prediction

Abstract

Modeling powerful interactions is a critical challenge in Click-through rate (CTR) prediction, which is one of the most typical machine learning tasks in personalized advertising and recommender systems. Although developing hand-crafted interactions is effective for a small number of datasets, it generally requires laborious and tedious architecture engineering for extensive scenarios. In recent years, several neural architecture search (NAS) methods have been proposed for designing interactions automatically. However, existing methods only explore limited types and connections of operators for interaction generation, leading to low generalization ability. To address these problems, we propose a more general automated method for building powerful interactions named AutoPI. The main contributions of this paper are as follows: AutoPI adopts a more general search space in which the computational graph is generalized from existing network connections, and the interactive operators in the edges of the graph are extracted from representative hand-crafted works. It allows searching for various powerful feature interactions to produce higher AUC and lower Logloss in a wide variety of applications. Besides, AutoPI utilizes a gradient-based search strategy for exploration with a significantly low computational cost. Experimentally, we evaluate AutoPI on a diverse suite of benchmark datasets, demonstrating the generalizability and efficiency of AutoPI over hand-crafted architectures and state-of-the-art NAS algorithms.

arXiv commentAccepted by ACM SIGIR 2021

References in corpus (18)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Neural Architecture Search: A Survey
• xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
• Efficient Neural Architecture Search via Parameter Sharing
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
• FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction
• DARTS+: Improved Differentiable Architecture Search with Early Stopping
• A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
• Feature Generation by Convolutional Neural Network for Click-Through Rate Prediction
• Towards Automated Neural Interaction Discovery for Click-Through Rate Prediction
• Deep & Cross Network for Ad Click Predictions
• Generalized Score Matching for Non-Negative Data
• Noisy Differentiable Architecture Search
• AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications
• AutoRec: An Automated Recommender System

Cited by in corpus (3)

• Click-Through Rate Prediction in Online Advertising: A Literature Review
• CL4CTR: A Contrastive Learning Framework for CTR Prediction
• OptEmbed: Learning Optimal Embedding Table for Click-through Rate Prediction