{"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/siamese-graph-learning-for-semi-supervised","title":"Siamese Graph Learning for Semi-supervised Age Estimation","arxiv_id":null,"date":"2023-03-13","proceeding":"journal 2023 3","authors":["Hao Liu; Mei Ma; Zixian Gao; Zongyong Deng; Fengjun Li; Zhendong Li"],"abstract":"In this paper, we propose a Siamese graph learning (SGL) approach to alleviate aging dataset bias. While numerous semi-supervised algorithms have been successfully applied to classification tasks, most of them assume that both the labeled and unlabeled samples are drawn from identical distributions. However, this assumption may not hold due to the heterogeneity of face aging data, which gives rise to a bias and unpromising prediction. Motivated by this, our SGL learns to align the sparse distribution with the dense one for dataset debias with preserving the real aging smoothness. To achieve this, we adopt a mixup strategy to plausibly generate hallucinatory samples, which leverages amounts of unlabeled data to enhance the diversity of unbalanced classes. Moreover, we develop a graph contrastive regularization to suppress the noise introduced by auxiliary unlabeled samples. Extensive experimental results show compelling performance by only utilizing the limited scalability of training annotations.","url_abs":"https://ieeexplore.ieee.org/abstract/document/10068268","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10068268","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":"siamese-graph-learning-for-semi-supervised","repo_url":"https://github.com/2023-MindSpore-4/Code12/tree/main/liuhao/Siamese%20Graph%20Learning%20for%20Semi-supervised%20Age%20Estimation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"age-estimation","task_name":"Age Estimation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"graph-learning","task_name":"Graph Learning"}],"methods":[{"method_slug":"align","method_name":"ALIGN"},{"method_slug":"mixup","method_name":"Mixup"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}