Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings

Abstract

Click-through rate (CTR) prediction has been one of the most central problems in computational advertising. Lately, embedding techniques that produce low-dimensional representations of ad IDs drastically improve CTR prediction accuracies. However, such learning techniques are data demanding and work poorly on new ads with little logging data, which is known as the cold-start problem. In this paper, we aim to improve CTR predictions during both the cold-start phase and the warm-up phase when a new ad is added to the candidate pool. We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs. The proposed method trains an embedding generator for new ad IDs by making use of previously learned ads through gradient-based meta-learning. In other words, our method learns how to learn better embeddings. When a new ad comes, the trained generator initializes the embedding of its ID by feeding its contents and attributes. Next, the generated embedding can speed up the model fitting during the warm-up phase when a few labeled examples are available, compared to the existing initialization methods. Experimental results on three real-world datasets showed that Meta-Embedding can significantly improve both the cold-start and warm-up performances for six existing CTR prediction models, ranging from lightweight models such as Factorization Machines to complicated deep models such as PNN and DeepFM. All of the above apply to conversion rate (CVR) predictions as well.

Accepted at SIGIR 2019

References in corpus (2)

• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Cold-start Problems in Recommendation Systems via Contextual-bandit Algorithms

Cited by in corpus (8)

• Contrastive Collaborative Filtering for Cold-Start Item Recommendation
• User-Centric Conversational Recommendation with Multi-Aspect User Modeling
• Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencoder
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• AutoAssign+: Automatic Shared Embedding Assignment in Streaming Recommendation
• Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
• Bootstrapping Contrastive Learning Enhanced Music Cold-Start Matching
• Sequential Recommendation for Cold-start Users with Meta Transitional Learning