.png){kind=icon}
返回
Which Samples Should Be Learned First: Easy or Hard?
.png){kind=icon}
OA
AI
DOI：10.1109/TNNLS.2023.3284430.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Treating each training sample unequally is prevalent in many machine-learning tasks. Numerous weighting schemes have been proposed. Some schemes take the easy-first mode, whereas others take the hard-first one. Naturally, an interesting yet realistic question is raised. Given a new learning task, which samples should be learned first, easy or hard? To answer this question, both theoretical analysis and experimental verification are conducted. First, a general objective function is proposed and the optimal weight can be derived from it, which reveals the relationship between the difficulty distribution of the training set and the priority mode. Two novel findings are subsequently obtained: besides the easy-first and hard-first modes, there are two other typical modes, namely, medium-first and two-ends-first; the priority mode may be varied if the difficulty distribution of the training set changes greatly. Second, inspired by the findings, a flexible weighting scheme (FlexW) is proposed for selecting the optimal priority mode when there is no prior knowledge or theoretical clues. The four priority modes can be flexibly switched in the proposed solution, thus suitable for various scenarios. Third, a wide range of experiments is conducted to verify the effectiveness of our proposed FlexW and further compare the weighting schemes in different modes under various learning scenarios. On the basis of these works, reasonable and comprehensive answers are obtained for the easy-or-hard question.
Keyword:
Bias-variance tradeoff
easy-first
hard-first
learning difficulty
priority mode
weighting strategy
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
.png){kind=icon}
Haze Optical Properties from Long-Term Ground-Based Remote Sensing over Beijing and Xuzhou, China
OAAI
OAAI分享收藏Psychometrics of the Child PTSD Symptom Scale for DSM-5 for Trauma-Exposed Children and AdolescentsOAAI
OAAI分享收藏Dynamically Weighted Balanced Loss: Class Imbalanced Learning and Confidence Calibration of Deep Neural Networks动态加权平衡损失: 深度神经网络的类不平衡学习和置信度校准
PREAI
分享收藏Credit Card Fraud Detection: A Realistic Modeling and a Novel Learning Strategy信用卡欺诈检测: 现实的建模和新颖的学习策略OAAI
OAAI分享收藏分享收藏
查看更多内容