.png){kind=icon}
返回
Robust Multitask Learning With Sample Gradient Similarity
.png){kind=icon}
PRE
AI
DOI：10.1109/TSMC.2023.3315541.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Multitask learning has led to great success in many deep learning applications during the last decade. However, recent experiments have demonstrated that the performance of multitask learning depends on how to balance the relationship between different tasks. Therefore, many approaches have been proposed to adjust per-task gradient directions or design a more appropriate task reweighting scheme based on task-level statistics. In this article, we discuss how to boost the performance of multitask learning by using more fine-grained sample gradient information. To this end, we propose the concept of sample gradient similarity, which measures the agreement between the sample gradient for a task and the true gradient. Based on this concept, greater weight is assigned to more consistent tasks and more robust training samples to improve the training process of multitask learning. Extensive experimental results show that our proposed method outperforms the state-of-the-art algorithms on a series of challenging multitask datasets.
Keyword:
Deep learning
Automation
multitask learning
sample gradient
sample reweighting
task reweighting
期刊
IF:
10.5
论文数:
1.1W
被引数:
5.0W
机构
引用论文
.png){kind=icon}
Early Lane Change Prediction for Automated Driving Systems Using Multi-Task Attention-Based Convolutional Neural Networks基于多任务注意力的卷积神经网络的自动驾驶系统早期换道预测
OAAI
OAAI分享收藏Sampling Methods for Efficient Training of Graph Convolutional Networks: A Survey图卷积网络高效训练的抽样方法综述OAAI
OAAI分享收藏Multi-Modal Domain Adaptation Variational Auto-encoder for EEG-Based Emotion Recognition基于多模态域自适应变分自动编码器的EEG情感识别
PREAI
分享收藏SwinFusion: Cross-domain Long-range Learning for General Image Fusion via Swin TransformerSwinFusion: 通过Swin变压器进行通用图像融合的跨域远程学习
PREAI
分享收藏分享收藏Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation语义分割中领域适应的对抗性学习和自学技术
OAAI
OAAI分享收藏
查看更多内容