PML-ED: A method of partial multi-label learning by using encoder-decoder framework and exploring label correlation
Information Sciences(2024)
摘要
•A method of partial multi-label learning is proposed based on Encoder-Decoder.•A method generates credible label distribution by using KNN label attention.•Transformer-Block and CLN extract high-order label correlation.•Comprehensive analysis is based on twenty-three datasets across five evaluation criteria.
更多查看译文
关键词
Partial multi-label learning,Label correlation,Label disambiguation,Encoder-Decoder framework,Conditional layer normalization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要