Click-through Rate Prediction with Auto-Quantized Contrastive Learning

2021/09/27 by Yujie Pan, Jiangchao Yao, Pan, Yujie +9 · 1 citation
Computer Science · Decision Sciences · #Advanced Bandit Algorithms Research #Artificial Intelligence (cs.AI) #Caching and Content Delivery #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2109.13921

openalex publication_date 2021/09/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Click-through rate (CTR) prediction becomes indispensable in ubiquitous web recommendation applications. Nevertheless, the current methods are struggling under the cold-start scenarios where the user interactions are extremely sparse. We consider this problem as an automatic identification about whether the user behaviors are rich enough to capture the interests for prediction, and propose an Auto-Quantized Contrastive Learning (AQCL) loss to regularize the model. Different from previous methods, AQCL explores both the instance-instance and the instance-cluster similarity to robustify the latent representation, and automatically reduces the information loss to the active users due to the quantization. The proposed framework is agnostic to different model architectures and can be trained in an end-to-end fashion. Extensive results show that it consistently improves the current state-of-the-art CTR models.

Citations

• Item-based top-Nrecommendation algorithms
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Self-Supervised Learning by Cross-Modal Audio-Video Clustering
• ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
• On Mutual Information in Contrastive Learning for Visual Representations
• Momentum Contrast for Unsupervised Visual Representation Learning

Cited by

• PCR-CA: Parallel Codebook Representations with Contrastive Alignment for Multiple-Category App Recommendation

Related

• MAP: A Model-agnostic Pretraining Framework for Click-through Rate Prediction
• Deep Learning for Click-Through Rate Estimation
• Iterative Boosting Deep Neural Networks for Predicting Click-Through Rate
• Representation Learning-Assisted Click-Through Rate Prediction
• Deep Multiple Quantization Network on Long Behavior Sequence for Click-Through Rate Prediction