{"type":"ScholarlyArticle","title":"Predicting Spectral Information for Self-Supervised Signal Classification","authors":[{"name":"Yi Xu","slug":"yi-xu","given":"Yi","family":"Xu","affiliation":""},{"name":"Shuang Wang","slug":"shuang-wang","given":"Shuang","family":"Wang","affiliation":""},{"name":"Hantong Xing","slug":"hantong-xing","given":"Hantong","family":"Xing","affiliation":""},{"name":"Chenxu Wang","slug":"chenxu-wang","given":"Chenxu","family":"Wang","affiliation":""},{"name":"Dou Quan","slug":"dou-quan","given":"Dou","family":"Quan","affiliation":""},{"name":"Rui Yang","slug":"rui-yang","given":"Rui","family":"Yang","affiliation":""},{"name":"Dong Zhao","slug":"dong-zhao","given":"Dong","family":"Zhao","affiliation":""},{"name":"Luyang Mei","slug":"luyang-mei","given":"Luyang","family":"Mei","affiliation":""}],"abstract":"Deep learning methods have demonstrated remarkable performance across various communication signal processing tasks. However, most signal classification methods require a substantial amount of labeled samples for training, posing significant challenges in the field of communication signals, as labeling necessitates expert knowledge. This paper proposes a novel self-supervised signal classification method called Spectral-Guided Self-Supervised Signal Classification (SGSSC). Specifically, to leverage frequency-domain information with modulation semantics as prior knowledge for the model, we design a previously unexplored pretext task tailored to the format of signal data. This task involves predicting spectral information from masked time-domain signals, enabling the model to learn implicit signal features through cross-domain pattern transformation. Furthermore, the pretext task in the SGSSC method is relevant to the downstream classification task, and using traditional fine-tuning strategies on the downstream task may lead to the loss of certain features associated with the pretext task. Therefore, we propose an attention mechanism-based fine-tuning strategy that adaptively integrates pre-trained features from different levels. Extensive experimental results validate the superiority of the SGSSC method. For instance, when the proportion of labeled samples is only 0.5%, our method achieves an average improvement of 2.3% in downstream classification tasks compared to the best-performing self-supervised training strategies.","doi":"10.24963/ijcai.2025/752","url":"https://ijcai.org/proceedings/2025/752","pdf":"https://ijcai.org/proceedings/2025/0752.pdf","markdown":"https://ijcai.org/proceedings/2025/752.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/752","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Machine Learning","track":"Main Track","number":752,"pages":{"first":6758,"last":6766},"keywords":["Machine Learning: ML: Time series and data streams","Machine Learning: ML: Classification","Machine Learning: ML: Self-supervised Learning","Machine Learning: ML: Representation learning"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}