.png){kind=icon}
返回
Multi-task classification with sequential instances and tasks
.png){kind=icon}
OA
AI
DOI：10.1016/j.image.2018.02.013.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we propose a novel multi-task classification framework, called Multi-Task classification with Sequential Instances and Tasks (MTSIT). Different from previous works, which treat all tasks and instances equally, MTSIT is inspired by the cognitive process of human brain that often learns from easier tasks to harder tasks. Specifically, the method attempts to jointly learn the task curriculum (learning order of tasks) and the instance curriculum (learning order of instances) by introducing a self-paced item for the instances of each task in the existing multi-task learning framework Sequential Multi-Task learning (SeqMT), which transfers information from the previously learned tasks to the next ones through shared task parameters. To effectively solve MTSIT, we also propose an optimization algorithm in which the instance curriculum and the task curriculum alternate between two paradigms, Tasks-to-Instances and Instances-to-Tasks (TILT). In the tasks-to-instances step, the learner conducts the instance curriculum when the task curriculum has been fixed, while in the instances-to tasks step, the task curriculum is learned when the instance curriculum in each task has been settled down. Our TIIT method is based on an error bound of the proposed MTSIT. Experimental results on three real world datasets demonstrate the effectiveness of our method.
Keyword:
Classification
Multi-task learning
Curriculum learning
Self-paced learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
S
IF:
2.7
论文数:
2.8K
被引数:
4.2K
机构
引用论文
.png){kind=icon}
分享收藏
查看更多内容