DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction
Abstract
Learning feature interactions is important to the model performance of online advertising services. As a result, extensive efforts have been devoted to designing effective architectures to learn feature interactions. However, we observe that the practical performance of those designs can vary from dataset to dataset, even when the order of interactions claimed to be captured is the same. That indicates different designs may have different advantages and the interactions captured by them have non-overlapping information. Motivated by this observation, we propose DHEN - a deep and hierarchical ensemble architecture that can leverage strengths of heterogeneous interaction modules and learn a hierarchy of the interactions under different orders. To overcome the challenge brought by DHEN's deeper and multi-layer structure in training, we propose a novel co-designed training system that can further improve the training efficiency of DHEN. Experiments of DHEN on large-scale dataset from CTR prediction tasks attained 0.27\% improvement on the Normalized Entropy (NE) of prediction and 1.2x better training throughput than state-of-the-art baseline, demonstrating their effectiveness in practice.
Cite
@article{arxiv.2203.11014,
title = {DHEN: A Deep and Hierarchical Ensemble Network for Large-Scale Click-Through Rate Prediction},
author = {Buyun Zhang and Liang Luo and Xi Liu and Jay Li and Zeliang Chen and Weilin Zhang and Xiaohan Wei and Yuchen Hao and Michael Tsang and Wenjun Wang and Yang Liu and Huayu Li and Yasmine Badr and Jongsoo Park and Jiyan Yang and Dheevatsa Mudigere and Ellie Wen},
journal= {arXiv preprint arXiv:2203.11014},
year = {2022}
}