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

arXiv: https://arxiv.org/abs/2304.04959 · HTML: https://mlsanity.com/paper/2304.04959/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Apr 2023.

## Built on by (most cited first, 10 of 10)

- [Hierarchical LoRA MoE for Efficient CTR Model Scaling](https://mlsanity.com/paper/2510.10432/) (2025)
- [See Beyond a Single View: Multi-Attribution Learning Leads to Better Conversion Rate Prediction](https://mlsanity.com/paper/2508.15217/) (2025)
- [Leveraging Large Language Model-based Room-Object Relationships Knowledge for Enhancing Multimodal-Input Object Goal Navigation](https://mlsanity.com/paper/2403.14163/) (2024)
- [MultiBalance: Multi-Objective Gradient Balancing in Industrial-Scale Multi-Task Recommendation System](https://mlsanity.com/paper/2411.11871/) (2024)
- [Probabilistic Hyper-Graphs using Multiple Randomly Masked Autoencoders for Semi-supervised Multi-modal Multi-task Learning](https://mlsanity.com/paper/2510.10068/) (2025)
- [Jointly Optimizing Debiased CTR and Uplift for Coupons Marketing: A Unified Causal Framework](https://mlsanity.com/paper/2602.12972/) (2026)
- [MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms](https://mlsanity.com/paper/2603.02184/) (2026)
- [Efficient Multi-Task Modeling through Automated Fusion of Trained Models](https://mlsanity.com/paper/2504.09812/) (2025)
- [Large Scalable Cross-Domain Graph Neural Networks for Personalized Notification at LinkedIn](https://mlsanity.com/paper/2506.12700/) (2025)
- [Lightweight Ranking Heads: Accelerating Multi-Task Experimentation in Production Recommender Systems](https://mlsanity.com/paper/2609.25433/) (2026)

## Abstract (arXiv)

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.