.png){kind=icon}
返回
Feature-Based Transfer Learning Based on Distribution Similarity
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2018.2843773.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Transfer learning has been found helpful at enhancing the target domain's learning process by transferring useful knowledge from other different but related source domains. In many applications, however, collecting and labeling target information is not only very difficult but also expensive. At the same time, considerable prior experience in this regard exists in other application domains. This paper proposes a feature-based transfer learning method based on distribution similarity that aims at the partial overlap of features between two domains. The non-overlapping features are completed by leveraging the distribution similarity of other features within the source domain. Features of the two domains are then reweighted in accordance with the distribution similarity between the source and target domains. This, in turn, decreases the distribution discrepancy between the two domains, therefore achieving the desired feature transfer. Results of the experiments performed on Facebook and Sina Microblog data sets demonstrate that the proposed method is capable of effectively enhancing the accuracy of the prediction function.
Keyword:
Distribution similarity
feature transfer
KL divergence
transfer 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:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Weighting training images by maximizing distribution similarity for supervised segmentation across scanners.png)
MEDICAL IMAGE ANALYSIS
MEDICAL IMAGE ANALYSISIF11.8
PREAI
分享收藏RETRACTED: Investigation and Evaluation of the Hybrid System of Energy Storage for Renewable EnergiesEnergies
OAAI
EnergiesIF0
OAAI分享收藏
查看更多内容