Results 41 to 50 of about 3,537 (211)

Multi‐Task Learning for Simultaneous Retrievals of Passive Microwave Precipitation Estimates and Rain/No‐Rain Classification

Geophysical Research Letters, 2023
Satellite‐based precipitation estimations provide frequent, large‐scale measurements. Deep learning has recently shown significant potential for improving estimation accuracy.
Takumi Bannai, Haoyang Xu, Nobuyuki Utsumi, Eunho Koo, Keming Lu, Hyungjun Kim   +5 more
doaj   +1 more source

Stabilizing Multi-Task Latent Spaces: Recursive Refinement With Coordinators in Partially Labeled Learning

IEEE Access
Multi-Task Learning (MTL) is a widely used paradigm that enhances generalization by training multiple tasks simultaneously. However, it requires large datasets where each sample must have labels for all tasks, making it costly and impractical.
Wooseong Jeong, Jegyeong Cho, Youngho Yoon, Jaeyoung Lee, Kuk-Jin Yoon   +4 more
doaj   +1 more source

QGeoSEP: A Novel Multi‐Task Learning Framework Integrating Quantum, Geometric, and Semantic Features for Collaborative Prediction of Multiple Properties With Potential Application to Energetic Materials

Materials Genome Engineering Advances, EarlyView.
We introduce QGeoSEP, a multi‐task learning framework for accurate energetic material property prediction, with competitive performance against mainstream baselines and an accessible online tool for efficient molecular evaluation. ABSTRACT Accurate physicochemical property prediction is critical for the rational design of energetic materials (EMs), yet
Mingchi Gao, Zhijiang Yang, Tengxin Huang, Yingjun Zhang, Liangliang Wang, Junjie Ding, Mingtian Li   +6 more
wiley   +1 more source

Equitable Multi-task Learning

, 2023
Multi-task learning (MTL) has achieved great success in various research domains, such as CV, NLP and IR etc. Due to the complex and competing task correlation, naive training all tasks may lead to inequitable learning, i.e.
Yuan, Jun, Zhang, Rui
core  

Recommendation Algorithm for Multi-Task Learning with Directed Graph Convolutional Networks

Applied Sciences, 2022
As an important branch of machine learning, recommendation algorithms have attracted the attention of many experts and scholars. The current recommendation algorithms all more or less have problems such as cold start and single recommended items.
Lifeng Yin, Jianzheng Lu, Guanghai Zheng, Huayue Chen, Wu Deng   +4 more
doaj   +1 more source

M3LoRA: Flexible Task Adaptation via Multiple Low‐Rank Matrices With Mixture‐of‐Subspaces and Minor Singular Components Initialization

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Parameter‐efficient fine‐tuning (PEFT) has become a crucial paradigm for domain adaptation, achieving strong performance by updating only a small fraction of model parameters. Among various PEFT methods, low‐rank adaptation (LoRA) is widely adopted due to its structural simplicity and computational efficiency.
Xu Luo, Yongbin Liu, Chunping Ouyang, Ying Yu, Yang Yang   +4 more
wiley   +1 more source

Structure Learning in Deep Multi-Task Models [PDF]

, 2023
Multi-Task Learning (MTL) aims at improving the learning process by solving different tasks simultaneously. Two general approaches for neural MTL are hard and soft information sharing during training. Here we propose two new approaches to neural MTL. The
Dorronsoro Ibero, José Ramón, Alaiz Gudín, Carlos María, Ruiz Pastor, Carlos   +2 more
core   +1 more source

A Novel Multi-Task Learning Model with PSAE Network for Simultaneous Estimation of Surface Quality and Tool Wear in Milling of Nickel-Based Superalloy Haynes 230

Sensors, 2022
For data-driven intelligent manufacturing, many important in-process parameters should be estimated simultaneously to control the machining precision of the parts. However, as two of the most important in-process parameters, there is a lack of multi-task
Minghui Cheng, Li Jiao, Pei Yan, Huiqing Gu, Jie Sun, Tianyang Qiu, Xibin Wang   +6 more
doaj   +1 more source

MTL-NAS: Task-Agnostic Neural Architecture Search Towards General-Purpose Multi-Task Learning

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
We propose to incorporate neural architecture search (NAS) into general-purpose multi-task learning (GP-MTL). Existing NAS methods typically define different search spaces according to different tasks. In order to adapt to different task combinations (i.e., task sets), we disentangle the GP-MTL networks into single-task backbones (optionally encode the
Yuan Gao 0015, Haoping Bai, Zequn Jie, Jiayi Ma 0001, Kui Jia, Wei Liu 0005   +5 more
openaire   +2 more sources

Neural Network Repair With Shapley‐Guided Search

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT The deployment of deep neural networks (DNNs) in safety‐critical domains is critically hampered by their vulnerability to defects, which can arise from malicious attacks or low‐quality data. Therefore, precisely locating the network components responsible for these defects, and subsequently repairing them without compromising overall model ...
Xiaofu Du, Zixiong Zhang, Xuesong Wang, Linqiang Liu, Junyan Qian   +4 more
wiley   +1 more source