{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/subject-aware-contrastive-learning-for","title":"Subject-Aware Contrastive Learning for Biosignals","arxiv_id":"2007.04871","date":"2020-06-30","proceeding":null,"authors":["Joseph Y. Cheng","Hanlin Goh","Kaan Dogrusoz","Oncel Tuzel","Erdrin Azemi"],"abstract":"Datasets for biosignals, such as electroencephalogram (EEG) and electrocardiogram (ECG), often have noisy labels and have limited number of subjects (<100). To handle these challenges, we propose a self-supervised approach based on contrastive learning to model biosignals with a reduced reliance on labeled data and with fewer subjects. In this regime of limited labels and subjects, intersubject variability negatively impacts model performance. Thus, we introduce subject-aware learning through (1) a subject-specific contrastive loss, and (2) an adversarial training to promote subject-invariance during the self-supervised learning. We also develop a number of time-series data augmentation techniques to be used with the contrastive loss for biosignals. Our method is evaluated on publicly available datasets of two different biosignals with different tasks: EEG decoding and ECG anomaly detection. The embeddings learned using self-supervision yield competitive classification results compared to entirely supervised methods. We show that subject-invariance improves representation quality for these tasks, and observe that subject-specific loss increases performance when fine-tuning with supervised labels.","url_abs":"https://arxiv.org/abs/2007.04871v1","url_pdf":"https://arxiv.org/pdf/2007.04871v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"subject-aware-contrastive-learning-for","repo_url":"https://github.com/zacharycbrown/ssl_baselines_for_biosignal_feature_extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg-4-classes","task_name":"EEG 4 classes"},{"task_slug":"eeg-left-right-hand","task_name":"EEG Left/Right hand"},{"task_slug":"eeg-decoding","task_name":"Eeg Decoding"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"person-identification","task_name":"Person Identification"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[{"method_slug":"1d-cnn","method_name":"1D CNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/person-identification-on-eeg-motor-movement","task":"Person Identification","dataset":"EEG Motor Movement/Imagery Dataset","model":"SSL","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"0.886"},"uses_additional_data":false},{"leaderboard":"/sota/person-identification-on-eeg-motor-movement","task":"Person Identification","dataset":"EEG Motor Movement/Imagery Dataset","model":"Subject-invariant SSL Embedding & Linear Classifier","rank_in_archive_order":2,"of":3,"metrics":{"Accuracy":"0.73"},"uses_additional_data":false},{"leaderboard":"/sota/person-identification-on-eeg-motor-movement","task":"Person Identification","dataset":"EEG Motor Movement/Imagery Dataset","model":"Subject-specific SSL","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy":"0.684"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.04871","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}