KMS of Xinjiang Astronomical Observatory, CAS
| A Graph-Based Semi-Supervised Approach for Few-Shot Class-Incremental Modulation Classification | |
Zhou, Xiaoyu1; Qi, Peihan1; Liu, Qi2 ; Ding, Yuanlei1; Zheng, Shilian3; Li, Zan1
| |
| 2024-03-31 | |
| Source Publication | CHINA COMMUNICATIONS
 |
| ISSN | 1673-5447 |
| Pages | 16 |
| Abstract | With the successive application of deep learning (DL) in classification tasks, the DL -based modulation classification method has become the preference for its state-of-the-art performance. Nevertheless, once the DL recognition model is pre -trained with fixed classes, the pre -trained model tends to predict incorrect results when identifying incremental classes. Moreover, the incremental classes are usually emergent without label information or only a few labeled samples of incremental classes can be obtained. In this context, we propose a graphbased semi -supervised approach to address the fewshot classes -incremental (FSCI) modulation classification problem. Our proposed method is a twostage learning method, specifically, a warm-up model is trained for classifying old classes and incremental classes, where the unlabeled samples of incremental classes are uniformly labeled with the same label to alleviate the damage of the class imbalance problem. Then the warm-up model is regarded as a feature extractor for constructing a similar graph to connect labeled samples and unlabeled samples, and the label propagation algorithm is adopted to propagate the label information from labeled nodes to unlabeled nodes in the graph to achieve the purpose of incremental classes recognition. Simulation results prove that the proposed method is superior to other finetuning methods and retrain methods. |
| Corresponding Author | Qi, Peihan(phqi@xidian.edu.cn) |
| Keyword | deep learning few-shot label propaga- tion modulation classification semi-supervised learn- ing |
| DOI | 10.23919/JCC.ea.2022-0339.202401 |
| Indexed By | SCI ; SCI |
| Language | 英语 |
| Funding Project | National Natural Science Foundation of China[62171334] ; National Natural Science Foundation of China[11973077] ; National Natural Science Foundation of China[12003061] |
| WOS Research Area | Telecommunications |
| WOS Subject | Telecommunications |
| WOS ID | WOS:001196701600001 |
| Publisher | CHINA INST COMMUNICATIONS |
| Funding Organization | National Natural Science Foundation of China |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.xao.ac.cn/handle/45760611-7/6227 |
| Collection | 中国科学院新疆天文台 |
| Corresponding Author | Qi, Peihan |
| Affiliation | 1.Xidian Univ, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China 2.Chinese Acad Sci, Xinjiang Astron Observ, Urumqi 830011, Peoples R China 3.011 Res Ctr, Sci & Technol Commun Informat Secur Control Lab, Jiaxing 314033, Peoples R China |
| Recommended Citation GB/T 7714 | Zhou, Xiaoyu,Qi, Peihan,Liu, Qi,et al. A Graph-Based Semi-Supervised Approach for Few-Shot Class-Incremental Modulation Classification[J]. CHINA COMMUNICATIONS,2024:16. |
| APA | Zhou, Xiaoyu,Qi, Peihan,Liu, Qi,Ding, Yuanlei,Zheng, Shilian,&Li, Zan.(2024).A Graph-Based Semi-Supervised Approach for Few-Shot Class-Incremental Modulation Classification.CHINA COMMUNICATIONS,16. |
| MLA | Zhou, Xiaoyu,et al."A Graph-Based Semi-Supervised Approach for Few-Shot Class-Incremental Modulation Classification".CHINA COMMUNICATIONS (2024):16. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment