Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 22 (2022)  /  Artículo
ARTÍCULO
TITULO

Adaptive Dynamic Search for Multi-Task Learning

Eunwoo Kim    

Resumen

Multi-task learning (MTL) is a learning strategy for solving multiple tasks simultaneously while exploiting commonalities and differences between tasks for improved learning efficiency and prediction performance. Despite its potential, there remain several major challenges to be addressed. First of all, the task performance degrades when the number of tasks to solve increases or the tasks are less related. In addition, finding the prediction model for each task is typically laborious and can be suboptimal. This nature of manually designing the architecture further aggravates the problem when it comes to solving multiple tasks under different computational budgets. In this work, we propose a novel MTL approach to address these issues. The proposed method learns to search in a finely modularized base network dynamically and to discover an optimal prediction model for each instance of a task on the fly while taking the computational costs of the discovered models into account. We evaluate our learning framework on a diverse set of MTL scenarios comprising standard benchmark datasets. We achieve significant improvements in performance for all tested cases compared with existing MTL alternatives.

 Artículos similares

       
 
Abdelghani Azri, Adil Haddi and Hakim Allali    
Collaborative filtering (CF), a fundamental technique in personalized Recommender Systems, operates by leveraging user?item preference interactions. Matrix factorization remains one of the most prevalent CF-based methods. However, recent advancements in ... ver más
Revista: Information

 
Zilin Zhao, Zhi Cai, Mengmeng Chang and Zhiming Ding    
Unconventional events exacerbate the imbalance between regional transportation demand and limited road network resources. Scientific and efficient path planning serves as the foundation for rapidly restoring equilibrium to the road network. In real large... ver más
Revista: Applied Sciences

 
Baobao Liu, Heying Wang, Zifan Cao, Yu Wang, Lu Tao, Jingjing Yang and Kaibing Zhang    
Defect detection holds significant importance in improving the overall quality of fabric manufacturing. To improve the effectiveness and accuracy of fabric defect detection, we propose the PRC-Light YOLO model for fabric defect detection and establish a ... ver más
Revista: Applied Sciences

 
Erman Ozpolat and Arif Gulten    
This paper explores the synchronization and implementation of a novel hyperchaotic system using an adaptive observer. Hyperchaotic systems, known for possessing a greater number of positive Lyapunov exponents compared to chaotic systems, present unique c... ver más
Revista: Applied Sciences

 
Nattakan Supajaidee, Nawinda Chutsagulprom and Sompop Moonchai    
Ordinary kriging (OK) is a popular interpolation method for its ability to simultaneously minimize error variance and deliver statistically optimal and unbiased predictions. In this work, the adaptive moving window kriging with K-means clustering (AMWKK)... ver más
Revista: Algorithms