Generative Learning from Semantically Confused Label Distribution via Auto-Encoding Variational Bayes
Guardado en:
| Udgivet i: | Electronics vol. 14, no. 13 (2025), p. 2736-2752 |
|---|---|
| Hovedforfatter: | |
| Andre forfattere: | , , , , , |
| Udgivet: |
MDPI AG
|
| Fag: | |
| Online adgang: | Citation/Abstract Full Text + Graphics Full Text - PDF |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3229143783 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2079-9292 | ||
| 024 | 7 | |a 10.3390/electronics14132736 |2 doi | |
| 035 | |a 3229143783 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231458 |2 nlm | ||
| 100 | 1 | |a Li, Xinhai |u Zhongshan Power Supply Bureau, China Southern Power Grid Co., Ltd., Zhongshan 528400, China; zslixinhai@163.com (X.L.); 18923336915@163.com (C.M.); 13226086386@163.com (H.Z.) | |
| 245 | 1 | |a Generative Learning from Semantically Confused Label Distribution via Auto-Encoding Variational Bayes | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Label Distribution Learning (LDL) has emerged as a powerful paradigm for addressing label ambiguity, offering a more nuanced quantification of the instance–label relationship compared to traditional single-label and multi-label learning approaches. This paper focuses on the challenge of noisy label distributions, which is ubiquitous in real-world applications due to the annotator subjectivity, algorithmic biases, and experimental errors. Existing related LDL algorithms often assume a linear combination of true and random label distributions when modeling the noisy label distributions, an oversimplification that fails to capture the practical generation processes of noisy label distributions. Therefore, this paper introduces an assumption that the noise in label distributions primarily arises from the semantic confusion between labels and proposes a novel generative label distribution learning algorithm to model the confusion-based generation process of both the feature data and the noisy label distribution data. The proposed model is inferred using variational methods and its effectiveness is demonstrated through extensive experiments across various real-world datasets, showcasing its superiority in handling noisy label distributions. | |
| 653 | |a Design | ||
| 653 | |a Algorithms | ||
| 653 | |a Labels | ||
| 653 | |a Machine learning | ||
| 653 | |a Entropy | ||
| 653 | |a Learning | ||
| 653 | |a Variational methods | ||
| 653 | |a Semantics | ||
| 700 | 1 | |a Meng Chenxu |u Zhongshan Power Supply Bureau, China Southern Power Grid Co., Ltd., Zhongshan 528400, China; zslixinhai@163.com (X.L.); 18923336915@163.com (C.M.); 13226086386@163.com (H.Z.) | |
| 700 | 1 | |a Zhou, Heng |u Zhongshan Power Supply Bureau, China Southern Power Grid Co., Ltd., Zhongshan 528400, China; zslixinhai@163.com (X.L.); 18923336915@163.com (C.M.); 13226086386@163.com (H.Z.) | |
| 700 | 1 | |a Guo, Yi |u Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China; guo.yi@sjtu.edu.cn | |
| 700 | 1 | |a Bowen, Xue |u Department of Computing, The Hong Kong Polytechnic University, Hong Kong 999077, China; xuebowen801@gmail.com (B.X.); tianzu.yu@polyu.edu.hk (T.Y.) | |
| 700 | 1 | |a Yu Tianzuo |u Department of Computing, The Hong Kong Polytechnic University, Hong Kong 999077, China; xuebowen801@gmail.com (B.X.); tianzu.yu@polyu.edu.hk (T.Y.) | |
| 700 | 1 | |a Lu Yunan |u Department of Computing, The Hong Kong Polytechnic University, Hong Kong 999077, China; xuebowen801@gmail.com (B.X.); tianzu.yu@polyu.edu.hk (T.Y.) | |
| 773 | 0 | |t Electronics |g vol. 14, no. 13 (2025), p. 2736-2752 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3229143783/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text + Graphics |u https://www.proquest.com/docview/3229143783/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3229143783/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |