Partial Label Learning Based on Fully Connected Deep Neural Network

被引：0
作者：
Li H. [1 ]
Wu L. [1 ]
He J. [1 ]
Zheng R. [1 ]
Zhou Y. [1 ]
Qiao S. [2 ]
机构：
[1] College of Information and Communication Engineering, Dalian Minzu University, Dalian
[2] School of Management, Dalian Polytechnic University, Dalian
来源：
International Journal of Circuits, Systems and Signal Processing | 2022年 / 16卷
基金：
中国国家自然科学基金;
关键词：
Deep neural network; Partial label learning; Weakly annotated data;
D O I：
10.46300/9106.2022.16.35
中图分类号：
学科分类号：
摘要：
The ambiguity of training samples in the partial label learning framework makes it difficult for us to develop learning algorithms and most of the existing algorithms are proposed based on the traditional shallow machine learning models, such as decision tree, support vector machine, and Gaussian process model. Deep neural networks have demonstrated excellent performance in many application fields, but currently it is rarely used for partial label learning frame-work. This study proposes a new partial label learning algorithm based on a fully connected deep neural network, in which the relationship between the candidate labels and the ground-truth label of each training sample is established by defining three new loss functions, and a regularization term is added to prevent overfitting. The experimental results on the controlled U-CI datasets and real-world partial label datasets reveal that the proposed algorithm can achieve higher classification accuracy than the state-of-the-art partial label learning algorithms. © 2022, North Atlantic University Union NAUN. All rights reserved.
引用
收藏
页码：287 / 297
页数：10
相关论文
共 54 条
  • [1] Cour T., Sapp B., Taskar B., Learning from partial labels, Journal of Machine Learning Research, 12, pp. 1501-1536, (2011)
  • [2] Luo J., Orabona F., Learning from candidate labeling sets, Advances in neural information processing systems, pp. 1504-1512, (2010)
  • [3] Zeng Z., Xiao S., Jia K., Chan T.-H., Gao S., Xu D., Ma Y., Learning by associating ambiguously labeled images, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 708-715, (2013)
  • [4] Zhang M.-L., Zhou B.-B., Liu X.-Y., Partial label learning via feature-aware disambiguation, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Min-ing, pp. 1335-1344, (2016)
  • [5] Hullermeier E., Beringer J., Learning from ambiguously labeled examples, Intelligent Data Analy-sis, 10, 5, pp. 419-439, (2006)
  • [6] Zhang M.-L., Yu F., Solving the partial label learning problem: An instance-based approach, Twenty-Fourth International Joint Conference on Artificial Intelligence, pp. 4048-4054, (2015)
  • [7] Nguyen N., Caruana R., Classification with partial labels, Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 551-559, (2008)
  • [8] Yu F., Zhang M.-L., Maximum margin partial label learning, Machine Learning, 106, 4, pp. 573-593, (2017)
  • [9] Grandvalet Y., Logistic regression for partial labels, International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems, pp. 1935-1941, (2002)
  • [10] Beygelzimer A., Langford J., The offset tree for learning with partial labels, Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 129-138, (2009)
123456