AdaptDHM: Adaptive Distribution Hierarchical Model for Multi-Domain CTR Prediction

TL;DR

AdaptDHM introduces an end-to-end hierarchical model with a dynamic routing mechanism for multi-domain CTR prediction, effectively capturing domain distribution differences while reducing computational costs.

Contribution

It proposes a novel adaptive distribution clustering approach that eliminates the need for pre-defined domain grouping, enhancing model flexibility and efficiency.

Findings

Achieves higher prediction accuracy on public and industrial datasets.

Reduces training time by over 50% compared to existing models.

Effectively models multiple domain distributions without prior domain knowledge.

Abstract

Large-scale commercial platforms usually involve numerous business domains for diverse business strategies and expect their recommendation systems to provide click-through rate (CTR) predictions for multiple domains simultaneously. Existing promising and widely-used multi-domain models discover domain relationships by explicitly constructing domain-specific networks, but the computation and memory boost significantly with the increase of domains. To reduce computational complexity, manually grouping domains with particular business strategies is common in industrial applications. However, this pre-defined data partitioning way heavily relies on prior knowledge, and it may neglect the underlying data distribution of each domain, hence limiting the model's representation capability. Regarding the above issues, we propose an elegant and flexible multi-distribution modeling paradigm, named Adaptive Distribution Hierarchical Model (AdaptDHM), which is an end-to-end optimization hierarchical structure consisting of a clustering process and classification process. Specifically, we design a distribution adaptation module with a customized dynamic routing mechanism. Instead of introducing prior knowledge for pre-defined data allocation, this routing algorithm adaptively provides a distribution coefficient for each sample to determine which cluster it belongs to. Each cluster corresponds to a particular distribution so that the model can sufficiently capture the commonalities and distinctions between these distinct clusters. Extensive experiments on both public and large-scale Alibaba industrial datasets verify the effectiveness and efficiency of AdaptDHM: Our model achieves impressive prediction accuracy and its time cost during the training stage is more than 50% less than that of other models.