AdaTT: Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations

TL;DR

AdaTT introduces an adaptive fusion network for multitask learning in recommendation systems, effectively modeling task relationships and learning shared and task-specific knowledge, leading to superior performance over existing methods.

Contribution

The paper proposes AdaTT, a novel deep fusion network with adaptive task-to-task fusion units, addressing key challenges in multitask learning for recommendations.

Findings

AdaTT outperforms state-of-the-art baselines on benchmark datasets.

The model effectively learns shared and task-specific knowledge.

Experimental results show improved recommendation accuracy.

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.