.png){kind=icon}
返回
A theoretical analysis based on causal inference and single-instance learning
.png){kind=icon}
OA
AI
DOI：10.1007/s10489-022-03193-0.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Although using single-instance learning methods to solve multi-instance problems has achieved excellent performance in many tasks, the reasons for this success still lack a rigorous theoretical explanation. In particular, the potential relation between the number of causal factors (also called causal instances) in a bag and the model performance is not transparent. The goal of our study is to use the causal relationship between instances and bags to enhance the interpretability of multi-instance learning. First, we provide a lower bound on the number of instances required to determine causal factors in a real multi-instance learning task. Then, we provide a lower bound on the single-instance learning loss function when testing instances and training instances follow the same distribution and extend this conclusion to the situation where the distribution changes. Thus, theoretically, we demonstrate that the number of causal factors in the bag is an important parameter that affects the performance of the model when using single-instance learning methods to solve multi-instance learning problems. Finally, combining with a specific classification task, we experimentally validate our theoretical analysis.
Keyword:
Causal inference
Distribution change
Multi-instance learning
Single-instance 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
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
分享收藏Multi-instance clustering with applications to multi-instance prediction.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏
Synergistic learning of lung lobe segmentation and hierarchical multi-instance classification for automated severity assessment of COVID-19 in CT imagesPATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Multi-instance cancellable biometrics schemes based on generative adversarial network基于生成对抗网络的多实例可取消生物识别方案APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏Multiple-instance learning as a classifier combining problem作为分类器组合问题的多示例学习PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容