{"type":"ScholarlyArticle","title":"Label Distribution Learning from Logical Label","authors":[{"name":"Yuheng Jia","slug":"yuheng-jia","given":"Yuheng","family":"Jia","affiliation":"School of Computer Science and Engineering , Southeast University; Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) , Ministry of Education , China"},{"name":"Jiawei Tang","slug":"jiawei-tang","given":"Jiawei","family":"Tang","affiliation":"School of Computer Science and Engineering , Southeast University; Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) , Ministry of Education , China"},{"name":"Jiahao Jiang","slug":"jiahao-jiang","given":"Jiahao","family":"Jiang","affiliation":"School of Computer Science and Engineering , Southeast University; Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University) , Ministry of Education , China"}],"abstract":"Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. However, annotating label distribution (LD) for training samples is extremely costly. So recent studies often first use label enhancement (LE) to generate the estimated label distribution from the logical label and then apply external LDL algorithms on the recovered label distribution to predict the label distribution for unseen samples. But this step-wise manner overlooks the possible connections between LE and LDL. Moreover, the existing LE approaches may assign some description degrees to invalid labels. To solve the above problems, we propose a novel method to learn an LDL model directly from the logical label, which unifies LE and LDL into a joint model, and avoids the drawbacks of the previous LE methods. We also give the generalization error bound of our method and theoretically prove that directly learning an LDL model from the logical labels is feasible.  Extensive experiments on various datasets prove that the proposed approach can construct a reliable LDL model directly from the logical label, and produce more accurate label distribution than the state-of-the-art LE methods. The code and the supplementary file can be found in https://github.com/seutjw/DLDL.","doi":"10.24963/ijcai.2024/467","url":"https://ijcai.org/proceedings/2024/467","pdf":"https://ijcai.org/proceedings/2024/0467.pdf","markdown":"https://ijcai.org/proceedings/2024/467.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/467","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":467,"pages":{"first":4228,"last":4236},"keywords":["Machine Learning: ML: Multi-label learning","Machine Learning: ML: Optimization","Constraint Satisfaction and Optimization: CSO: Constraint optimization problems"],"videos":[],"references":[{"position":1,"raw":"[Berger et al., 1996] Adam L. Berger, Stephen Della Pietra, and Vincent J. Della Pietra. A maximum entropy approach to natural language processing. Computational Linguis- tics, 22(1):39-71, 1996.","title":"A maximum entropy approach to natural language processing","authors":"Adam L Berger, Stephen Della, Pietra, Vincent J Della, Pietra","year":"1996","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":2,"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 Artificial Neural Networks in Pattern Recognition, Second IAPR Workshop, 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":"Artificial Neural Networks in Pattern Recognition, Second IAPR Workshop","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Geng et al., 2022] Xin Geng, Renyi Zheng, Jiaqi Lv, and Yu Zhang. Multilabel ranking with inconsistent rankers. IEEE Transactions on Pattern Analysis & Machine Intelli- gence, 44(09):5211-5224, 2022.","title":"Multilabel ranking with inconsistent rankers","authors":"Xin Geng, Renyi Zheng, Jiaqi Lv, Yu Zhang","year":"2022","venue":"IEEE Transactions on Pattern Analysis & Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":4,"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":5,"raw":"[Jia et al., 2020a] Yuheng Jia, Hui Liu, Junhui Hou, and Sam Kwong. Clustering-aware graph construction: A joint learning perspective. IEEE Trans. Signal Inf. Process. over Networks, 6:357-370, 2020.","title":"Clustering-aware graph construction: A joint learning perspective","authors":"Jia","year":"2020","venue":"IEEE Trans. Signal Inf. Process. over Networks","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Jia et al., 2020b] Yuheng Jia, Hui Liu, Junhui Hou, and Sam Kwong. Pairwise constraint propagation with dual adver- sarial manifold regularization. IEEE Trans. Neural Net- works Learn. Syst., 31(12):5575-5587, 2020.","title":"Pairwise constraint propagation with dual adversarial manifold regularization","authors":"Jia","year":"2020","venue":"IEEE Trans. Neural Networks Learn. Syst","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Liang et al., 2018] Lingyu Liang, Luojun Lin, Lianwen Jin, Duorui Xie, and Mengru Li. SCUT-FBP5500: A di- verse benchmark dataset for multi-paradigm facial beauty prediction. In 24th International Conference on Pattern Recognition, pages 1598-1603. IEEE Computer Society, 2018.","title":"SCUT-FBP5500: A diverse benchmark dataset for multi-paradigm facial beauty prediction","authors":"Lingyu Liang, Luojun Lin, Lianwen Jin, Duorui Xie, Mengru Li","year":"2018","venue":"24th International Conference on Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Liu et al., 2021a] Xinyuan Liu, Jihua Zhu, Zhongyu Li, Zhiqiang Tian, Xiuyi Jia, and Lei Chen. Unified frame- work for learning with label distribution. Inf. Fusion, 75:116-130, 2021.","title":"Unified framework for learning with label distribution","authors":"Liu","year":"2021","venue":"Inf. Fusion","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2021b] Xinyuan Liu, Jihua Zhu, Qinghai Zheng, Zhongyu Li, Ruixin Liu, and Jun Wang. Bidirectional loss function for label enhancement and distribution learning. Knowledge-Based Systems, 213:106690, 2021.","title":"Bidirectional loss function for label enhancement and distribution learning","authors":"Liu","year":"2021","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Quan and Ren, 2009] Changqin Quan and Fuji Ren. Con- struction of a blog emotion corpus for chinese emotional expression analysis. In Proceedings of the 2009 confer- ence on empirical methods in natural language process- ing, pages 1446-1454, 2009.","title":"Changqin Quan and Fuji Ren. Construction of a blog emotion corpus for chinese emotional expression analysis","authors":"Ren Quan","year":"2009","venue":"Proceedings of the 2009 conference on empirical methods in natural language processing","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Shang and Deng, 2019] Li Shang and Weihong Deng. Blended emotion in-the-wild: Multi-label facial expres- sion recognition using crowdsourced annotations and deep locality feature learning. International Journal of Com- puter Vision, 127(6-7):884-906, 2019.","title":"Blended emotion in-the-wild: Multi-label facial expression recognition using crowdsourced annotations and deep locality feature learning","authors":"Li Shang, Weihong Deng","year":"2019","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Shao et al., 2018] Ruifeng Shao, Ning Xu, and Xin Geng. Multi-label learning with label enhancement. In 2018 IEEE International Conference on Data Mining (ICDM), pages 437-446, 2018.","title":"Multi-label learning with label enhancement","authors":"Shao","year":"2018","venue":"IEEE International Conference on Data Mining (ICDM)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Shen et al., 2017] Wei Shen, Kai Zhao, Yilu Guo, and Alan L. Yuille. Label distribution learning forests. CoRR, abs/1702.06086, 2017.","title":"Label distribution learning forests","authors":"Wei Shen, Kai Zhao, Yilu Guo, Alan L Yuille","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Tsoumakas and Katakis, 2007] Grigorios Tsoumakas and Ioannis Katakis. Multi-label classification: An overview. International Journal of Data Warehousing and Mining, 3(3):1-13, 2007.","title":"Grigorios Tsoumakas and Ioannis Katakis. Multi-label classification: An overview","authors":"Katakis Tsoumakas","year":"2007","venue":"International Journal of Data Warehousing and Mining","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Wang et al., 2023] Ke Wang, Ning Xu, Miaogen Ling, and Xin Geng. Fast label enhancement for label distribution learning. IEEE Transactions on Knowledge and Data En- gineering, 35(2):1502-1514, 2023.","title":"Fast label enhancement for label distribution learning","authors":"Ke Wang, Ning Xu, Miaogen Ling, Xin Geng","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Xie et al., 2015] Duorui Xie, Lingyu Liang, Lianwen Jin, Jie Xu, and Mengru Li. Scut-fbp: A benchmark dataset for facial beauty perception. In 2015 IEEE International Con- ference on Systems, Man, and Cybernetics, pages 1821- 1826, 2015.","title":"Scut-fbp: A benchmark dataset for facial beauty perception","authors":"Duorui Xie, Lingyu Liang, Lianwen Jin, Jie Xu, Mengru Li","year":"2015","venue":"IEEE International Conference on Systems, Man, and Cybernetics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xu et al., 2019] Suping Xu, Lin Shang, and Furao Shen. Latent semantics encoding for label distribution learning. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pages 3982-3988. ij- cai.org, 2019.","title":"Latent semantics encoding for label distribution learning","authors":"Xu","year":"2019","venue":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2019/553"},{"position":18,"raw":"[Xu et al., 2021] 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, 2021.","title":"Label enhancement for label distribution learning","authors":"Ning Xu, Yun-Peng Liu, Xin Geng","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":"/proceedings/2018/406"},{"position":19,"raw":"[Yang et al., 2016] Xu Yang, Xin Geng, and Deyu Zhou. Sparsity conditional energy label distribution learning for age estimation. In Proceedings of the Twenty-Fifth Inter- national Joint Conference on Artificial Intelligence, pages 2259-2265. IJCAI/AAAI Press, 2016.","title":"Sparsity conditional energy label distribution learning for age estimation","authors":"Xu Yang, Xin Geng, Deyu Zhou","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/322"},{"position":20,"raw":"[Yang et al., 2017] Jufeng Yang, Ming Sun, and Xiaoxiao Sun. Learning visual sentiment distributions via aug- mented conditional probability neural network. In Pro- ceedings of the Thirty-First AAAI Conference on Artificial Intelligence, pages 224-230. AAAI Press, 2017.","title":"Learning visual sentiment distributions via augmented conditional probability neural network","authors":"Jufeng Yang, Ming Sun, Xiaoxiao Sun","year":"2017","venue":"Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Zhang and Zhou, 2014] Min-Ling Zhang and Zhi-Hua Zhou. A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 26(8):1819-1837, 2014.","title":"A review on multi-label learning algorithms","authors":"Zhou ; ] Min-Ling Zhang, Zhi-Hua Zhang, Zhou","year":"2014","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Zhang et al., 2021] Min-Ling Zhang, Qian-Wen Zhang, Jun-Peng Fang, Yu-Kun Li, and Xin Geng. Leveraging implicit relative labeling-importance information for ef- fective multi-label learning. IEEE Transactions on Knowl- edge and Data Engineering, 33(5):2057-2070, 2021.","title":"Leveraging implicit relative labeling-importance information for effective multi-label learning","authors":"Zhang","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhao and Zhou, 2018] Peng Zhao and Zhi-Hua Zhou. La- bel distribution learning by optimal transport. In Proceed- ings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Sym- posium on Educational Advances in Artificial Intelligence (EAAI-18), pages 4506-4513. AAAI Press, 2018.","title":"Label distribution learning by optimal transport","authors":"Peng Zhao, Zhi-Hua Zhou","year":"2018","venue":"AAAI-18), the 30th innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18)","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zheng et al., 2023] 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, 35(1):482- 495, 2023.","title":"Generalized label enhancement with sample correlations","authors":"Zheng","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}