paper-with-me

홈 › Papers

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

2023-04-11 · Danwei Li, Zhengyu Zhang, Siyang Yuan, Mingze Gao, Weilin Zhang, Chaofei Yang, Xi Liu, Jiyan Yang

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.

📄 PDF Abstract BibTeX arXiv:2304.04959

Code (1)

facebookresearch/adatt 공식 구현 pytorch

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways

2026-03-23 · Soudeep Ghoshal, Himanshu Buckchash arxiv

Deep ConvNets suffer from gradient signal degradation as network depth increases, limiting effective feature learning in complex architectures. ResNet addressed this through residual connections, but these fixed short-ci…

Representation Learning

Robust Multitask Diffusion Normalized M-estimate Subband Adaptive Filtering Algorithm Over Adaptive Networks

2022-10-20 · Wenjing Xu, Haiquan Zhao, Shaohui Lv

In recent years, the multitask diffusion least mean square (MD-LMS) algorithm has been extensively applied in the distributed parameter estimation and target tracking of multitask network. However, its performance is mai…

parameter estimation

Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction

2021-12-04 · Yikai Wang, Fuchun Sun, Wenbing Huang, Fengxiang He 외

Multimodal fusion and multitask learning are two vital topics in machine learning. Despite the fruitful progress, existing methods for both problems are still brittle to the same challenge -- it remains dilemmatic to int…

Semantic Segmentation

Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality

2026-05-03 · Hanxiao Chen, Debarghya Mukherjee arxiv

We study clustered multitask learning in a semiparametric setting where tasks share a latent cluster structure in their target parameters but exhibit heterogeneous, potentially infinite-dimensional nuisance components. S…

Multitask diffusion adaptation over networks with common latent representations

2017-02-13 · Jie Chen, Cédric Richard, Ali H. Sayed

Online learning with streaming data in a distributed and collaborative manner can be useful in a wide range of applications. This topic has been receiving considerable attention in recent years with emphasis on both sing…