AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations
Abstract
Multi-task learning (MTL) aims to enhance the performance and efficiency of machine learning models by simultaneously training them on multiple tasks. However, MTL research faces two challenges: 1) effectively modeling the relationships between tasks to enable knowledge sharing, and 2) jointly learning task-specific and shared knowledge. In this paper, we present a novel model called Adaptive Task-to-Task Fusion Network (AdaTT) to address both challenges. AdaTT is a deep fusion network built with task-specific and optional shared fusion units at multiple levels. By leveraging a residual mechanism and a gating mechanism for task-to-task fusion, these units adaptively learn both shared knowledge and task-specific knowledge. To evaluate AdaTT's performance, we conduct experiments on a public benchmark and an industrial recommendation dataset using various task groups. Results demonstrate AdaTT significantly outperforms existing state-of-the-art baselines. Furthermore, our end-to-end experiments reveal that the model exhibits better performance compared to alternatives.
Cite
@article{arxiv.2304.04959,
title = {AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations},
author = {Danwei Li and Zhengyu Zhang and Siyang Yuan and Mingze Gao and Weilin Zhang and Chaofei Yang and Xi Liu and Jiyan Yang},
journal= {arXiv preprint arXiv:2304.04959},
year = {2023}
}