Towards Interpretable Deep Extreme Multi-label Learning
碩士 === 國立中山大學 === 資訊管理學系研究所 === 107 === Extreme multi-label learning is to seek most relevant subset of labels from an extreme large labels space. The problem of scalability and sparsity makes extreme multi-label hard to learn. In this paper, we propose a framework to deal with these problems. Our a...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
2019
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/t7hq7r |