{"type":"ScholarlyArticle","title":"Contrastive Label Enhancement","authors":[{"name":"Yifei Wang","slug":"yifei-wang","given":"Yifei","family":"Wang","affiliation":"School of Software Engineering , Xi'an Jiaotong University , Xi'an , China"},{"name":"Yiyang Zhou","slug":"yiyang-zhou","given":"Yiyang","family":"Zhou","affiliation":"School of Software Engineering , Xi'an Jiaotong University , Xi'an , China"},{"name":"Jihua Zhu","slug":"jihua-zhu","given":"Jihua","family":"Zhu","affiliation":"School of Software Engineering , Xi'an Jiaotong University , Xi'an , China"},{"name":"Xinyuan Liu","slug":"xinyuan-liu","given":"Xinyuan","family":"Liu","affiliation":"School of Software Engineering , Xi'an Jiaotong University , Xi'an , China"},{"name":"Wenbiao Yan","slug":"wenbiao-yan","given":"Wenbiao","family":"Yan","affiliation":"School of Software Engineering , Xi'an Jiaotong University , Xi'an , China"},{"name":"Zhiqiang Tian","slug":"zhiqiang-tian","given":"Zhiqiang","family":"Tian","affiliation":"School of Software Engineering , Xi'an Jiaotong University , Xi'an , China"}],"abstract":"Label distribution learning (LDL) is a new machine learning paradigm for solving label ambiguity. Since it is difficult to directly obtain label distributions, many studies are focusing on how to recover label distributions from logical labels, dubbed label enhancement (LE). Existing LE methods estimate label distributions by simply building a mapping relationship between features and label distributions under the supervision of logical labels. They typically overlook the fact that both features and logical labels are descriptions of the instance from different views. Therefore, we propose a novel method called Contrastive Label Enhancement (ConLE) which integrates features and logical labels into the unified projection space to generate high-level features by contrastive learning strategy. In this approach, features and logical labels belonging to the same sample are pulled closer, while those of different samples are projected farther away from each other in the projection space. Subsequently, we leverage the obtained high-level features to gain label distributions through a well-designed training strategy that considers the consistency of label attributes. Extensive experiments on LDL benchmark datasets demonstrate the effectiveness and superiority of our method.","doi":"10.24963/ijcai.2023/484","url":"https://ijcai.org/proceedings/2023/484","pdf":"https://ijcai.org/proceedings/2023/0484.pdf","markdown":"https://ijcai.org/proceedings/2023/484.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/484","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":484,"pages":{"first":4353,"last":4361},"keywords":["Machine Learning: ML: Multi-view learning","Machine Learning: ML: Multi-label"],"videos":[],"references":[{"position":1,"raw":"[Bai et al., 2022] Junwen Bai, Shufeng Kong, and Carla P Gomes. Gaussian mixture variational autoencoder with contrastive learning for multi-label classification. In Inter- national Conference on Machine Learning, pages 1383- 1398. PMLR, 2022.","title":"Gaussian mixture variational autoencoder with contrastive learning for multi-label classification","authors":"Bai","year":"2022","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Dai and Lin, 2017] Bo Dai and Dahua Lin. Contrastive learning for image captioning. Advances in Neural Infor- mation Processing Systems, 30, 2017.","title":"Contrastive learning for image captioning","authors":"Lin ; Dai, Bo Dai, Dahua Lin","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Eisen et al., 1998] Michael B Eisen, Paul T Spellman, Patrick O Brown, and David Botstein. Cluster analysis and display of genome-wide expression patterns. Proceed- ings of the National Academy of Sciences, 95(25):14863- 14868, 1998.","title":"Cluster analysis and display of genome-wide expression patterns","authors":"Paul T Michael B Eisen, Patrick O Spellman, David Brown, Botstein","year":"1998","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gao et al., 2021] Yongbiao Gao, Yu Zhang, and Xin Geng. Label enhancement for label distribution learning via prior knowledge. In Proceedings of the Twenty-Ninth Interna- tional Conference on International Joint Conferences on Artificial Intelligence, pages 3223-3229, 2021.","title":"Label enhancement for label distribution learning via prior knowledge","authors":"Gao","year":"2021","venue":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2020/446"},{"position":5,"raw":"[Gao et al., 2022] Yongbiao Gao, Ke Wang, and Xin Geng. Sequential label enhancement. IEEE Transactions on Neu- ral Networks and Learning Systems, 2022.","title":"Sequential label enhancement","authors":"Gao","year":"2022","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gayar et al., 2006] Neamat El Gayar, Friedhelm Schwenker, and Günther Palm. A study of the ro- bustness of knn classifiers trained using soft labels. In IAPR Workshop on Artificial Neural Networks in Pattern Recognition, pages 67-80. Springer, 2006.","title":"Neamat El Gayar, Friedhelm Schwenker, and Günther Palm. A study of the robustness of knn classifiers trained using soft labels","authors":"Gayar","year":"2006","venue":"IAPR Workshop on Artificial Neural Networks in Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Geng et al., 2013] Xin Geng, Chao Yin, and Zhi-Hua Zhou. Facial age estimation by learning from label distributions. IEEE transactions on pattern analysis and machine intel- ligence, 35(10):2401-2412, 2013.","title":"Facial age estimation by learning from label distributions","authors":"Xin Geng, Zhi-Hua Chao Yin, Zhou","year":"2013","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Geng, 2016] Xin Geng. Label distribution learning. IEEE Transactions on Knowledge and Data Engineering, 28(7):1734-1748, 2016.","title":"Label distribution learning","authors":"Xin Geng, Geng","year":"2016","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gibaja and Ventura, 2014] Eva Gibaja and Sebastián Ven- tura. Multi-label learning: a review of the state of the art and ongoing research. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 4(6):411-444, 2014.","title":"Eva Gibaja and Sebastián Ventura. Multi-label learning: a review of the state of the art and ongoing research","authors":"Ventura Gibaja","year":"2014","venue":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Grill et al., 2020] Jean-Bastien Grill, Florian Strub, Flo- rent Altché, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhao- han Guo, Mohammad Gheshlaghi Azar, et al. Bootstrap your own latent-a new approach to self-supervised learn- ing. Advances in neural information processing systems, 33:21271-21284, 2020.","title":"Bootstrap your own latent-a new approach to self-supervised learning","authors":"Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jiang et al., 2006] Xiufeng Jiang, Zhang Yi, and Jian Cheng Lv. Fuzzy svm with a new fuzzy membership function. Neural Computing & Applications, 15(3):268-276, 2006.","title":"Fuzzy svm with a new fuzzy membership function","authors":"Xiufeng Jiang, Zhang Yi, Jian Cheng, Lv","year":"2006","venue":"Neural Computing & Applications","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kanehira and Harada, 2016] Atsushi Kanehira and Tatsuya Harada. Multi-label ranking from positive and unlabeled data. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5138-5146, 2016.","title":"Multi-label ranking from positive and unlabeled data","authors":"Harada Kanehira, Atsushi Kanehira, Tatsuya Harada","year":"2016","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2015] Yu-Kun Li, Min-Ling Zhang, and Xin Geng. Leveraging implicit relative labeling-importance informa- tion for effective multi-label learning. In 2015 IEEE In- ternational Conference on Data Mining, pages 251-260. IEEE, 2015.","title":"Leveraging implicit relative labeling-importance information for effective multi-label learning","authors":"Li","year":"2015","venue":"IEEE International Conference on Data Mining","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2020] Junnan Li, Pan Zhou, Caiming Xiong, and Steven CH Hoi. Prototypical contrastive learn- ing of unsupervised representations. arXiv preprint arXiv:2005.04966, 2020.","title":"Prototypical contrastive learning of unsupervised representations","authors":"Li","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2021] Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, and Xi Peng. Contrastive cluster- ing. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 8547-8555, 2021.","title":"Contrastive clustering","authors":"Yunfan Li, Peng Hu, Zitao Liu, Dezhong Peng, Joey Tianyi Zhou, Xi Peng","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lyons et al., 1998] Michael Lyons, Shigeru Akamatsu, Miyuki Kamachi, and Jiro Gyoba. Coding facial expres- sions with gabor wavelets. In Proceedings Third IEEE international conference on automatic face and gesture recognition, pages 200-205. IEEE, 1998.","title":"Coding facial expressions with gabor wavelets","authors":"Michael Lyons, Shigeru Akamatsu, Miyuki Kamachi, Jiro Gyoba","year":"1998","venue":"Proceedings Third IEEE international conference on automatic face and gesture recognition","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Maas et al., 2013] Andrew L Maas, Awni Y Hannun, An- drew Y Ng, et al. Rectifier nonlinearities improve neu- ral network acoustic models. In Proc. icml, volume 30, page 3. Atlanta, Georgia, USA, 2013.","title":"Rectifier nonlinearities improve neural network acoustic models","authors":"Andrew L Maas, Andrew Y Awni Y Hannun, Ng","year":"2013","venue":"Proc. icml","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Moyano et al., 2019] Jose M Moyano, Eva L Gibaja, Krzysztof J Cios, and Sebastián Ventura. An evolution- ary approach to build ensembles of multi-label classifiers. Information Fusion, 50:168-180, 2019.","title":"An evolutionary approach to build ensembles of multi-label classifiers","authors":"Eva L Jose M Moyano, Krzysztof J Gibaja, Sebastián Cios, Ventura","year":"2019","venue":"Information Fusion","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Paszke et al., 2019] Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. Pytorch: An imperative style, high- performance deep learning library. Advances in neural in- formation processing systems, 32, 2019.","title":"Pytorch: An imperative style, highperformance deep learning library","authors":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga","year":"2019","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Qi et al., 2022] Lei Qi, Jiaying Shen, Jiaqi Liu, Yinghuan Shi, and Xin Geng. Label distribution learning for general- izable multi-source person re-identification. arXiv preprint arXiv:2204.05903, 2022.","title":"Label distribution learning for generalizable multi-source person re-identification","authors":"Lei Qi, Jiaying Shen, Jiaqi Liu, Yinghuan Shi, Xin Geng","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Qian et al., 2022] Shengsheng Qian, Dizhan Xue, Quan Fang, and Changsheng Xu. Integrating multi-label con- trastive learning with dual adversarial graph neural net- works for cross-modal retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1-18, 2022.","title":"Integrating multi-label contrastive learning with dual adversarial graph neural networks for cross-modal retrieval","authors":"Qian","year":"2022","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ruder, 2016] Sebastian Ruder. An overview of gradi- ent descent optimization algorithms. arXiv preprint arXiv:1609.04747, 2016.","title":"An overview of gradient descent optimization algorithms","authors":"Sebastian Ruder","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tang et al., 2020] Haoyu Tang, Jihua Zhu, Qinghai Zheng, Jun Wang, Shanmin Pang, and Zhongyu Li. Label en- hancement with sample correlations via low-rank repre- sentation. In Proceedings of the AAAI Conference on Arti- ficial Intelligence, volume 34, pages 5932-5939, 2020.","title":"Label enhancement with sample correlations via low-rank representation","authors":"Haoyu Tang, Jihua Zhu, Qinghai Zheng, Jun Wang, Shanmin Pang, Zhongyu Li","year":"2020","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2022] Ran Wang, Xinyu Dai, et al. Contrastive learning-enhanced nearest neighbor mechanism for multi- label text classification. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 672-679, 2022.","title":"Contrastive learning-enhanced nearest neighbor mechanism for multilabel text classification","authors":"Ran Wang, Xinyu Dai","year":"2022","venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Xu et al., 2019] Ning Xu, Yun-Peng Liu, and Xin Geng. Label enhancement for label distribution learning. IEEE Transactions on Knowledge and Data Engineering, 33(4):1632-1643, 2019.","title":"Label enhancement for label distribution learning","authors":"Ning Xu, Yun-Peng Liu, Xin Geng","year":"2019","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":"/proceedings/2018/406"},{"position":26,"raw":"[Xu et al., 2021] N. Xu, Y. Liu, and X. Geng. Label enhance- ment for label distribution learning. IEEE Transactions on Knowledge; Data Engineering, 33(04):1632-1643, apr 2021.","title":"Label enhancement for label distribution learning","authors":"N Xu, Y Liu, X Geng","year":"2021","venue":"IEEE Transactions on Knowledge; Data Engineering","doi":null,"url":null,"internal_url":"/proceedings/2018/406"},{"position":27,"raw":"[Xu et al., 2022] Ning Xu, Jun Shu, Renyi Zheng, Xin Geng, Deyu Meng, and Min-Ling Zhang. Variational label en- hancement. IEEE Transactions on Pattern Analysis & Ma- chine Intelligence, (01):1-15, 2022.","title":"Variational label enhancement","authors":"Ning Xu, Jun Shu, Renyi Zheng, Xin Geng, Deyu Meng, Min-Ling Zhang","year":"2022","venue":"IEEE Transactions on Pattern Analysis & Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yan et al., 2016] Yan Yan, Xu-Cheng Yin, Chun Yang, Bo- Wen Zhang, and Hong-Wei Hao. Multi-label ranking with lstm 2 for document classification. In Chinese Conference on Pattern Recognition, pages 349-363. Springer, 2016.","title":"Multi-label ranking with lstm 2 for document classification","authors":"Yan Yan, Xu-Cheng Yin, Chun Yang, Bo-Wen Zhang, Hong-Wei Hao","year":"2016","venue":"Chinese Conference on Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Yin et al., 2006] Lijun Yin, Xiaozhou Wei, Yi Sun, Jun Wang, and Matthew J Rosato. A 3d facial expression database for facial behavior research. In 7th interna- tional conference on automatic face and gesture recogni- tion (FGR06), pages 211-216. IEEE, 2006.","title":"A 3d facial expression database for facial behavior research","authors":"Lijun Yin, Xiaozhou Wei, Yi Sun, Jun Wang, Matthew J Rosato","year":"2006","venue":"7th international conference on automatic face and gesture recognition","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhang et al., 2015] Zhaoxiang Zhang, Mo Wang, and Xin Geng. Crowd counting in public video surveillance by la- bel distribution learning. Neurocomputing, 166:151-163, 2015.","title":"Crowd counting in public video surveillance by label distribution learning","authors":"Zhang","year":"2015","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang et al., 2022] Shu Zhang, Ran Xu, Caiming Xiong, and Chetan Ramaiah. Use all the labels: A hierarchical multi-label contrastive learning framework. In Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 16660-16669, 2022.","title":"Use all the labels: A hierarchical multi-label contrastive learning framework","authors":"Shu Zhang, Ran Xu, Caiming Xiong, Chetan Ramaiah","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhao et al., 2022] Xingyu Zhao, Yuexuan An, Ning Xu, and Xin Geng. Fusion label enhancement for multi-label learning. In Lud De Raedt, editor, Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 3773-3779. International Joint Conferences on Artificial Intelligence Organization, 7 2022. Main Track.","title":"Fusion label enhancement for multi-label learning","authors":"Xingyu Zhao, Yuexuan An, Ning Xu, Xin Geng","year":"2022","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22","doi":null,"url":null,"internal_url":"/proceedings/2022/524"},{"position":33,"raw":"[Zheng et al., 2021] Qinghai Zheng, Jihua Zhu, Haoyu Tang, Xinyuan Liu, Zhongyu Li, and Huimin Lu. Generalized label enhancement with sample correlations. IEEE Trans- actions on Knowledge and Data Engineering, 2021.","title":"Generalized label enhancement with sample correlations","authors":"Zheng","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}