Partial label learning (PLL) is a typical weakly supervised learning problem, where each training example is associated with a set of candidate labels among which only one is true. Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels. However, this assumption is not realistic since the candidate labels are always instance-dependent. In this paper, we consider instance-dependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature. The incorrect label with a high degree is more likely to be annotated as the candidate label. Therefore, the latent label distribution is the essential labeling information in partially labeled examples and worth being leveraged for predictive model training. Motivated by this consideration, we propose a novel PLL method that recovers the label distribution as a label enhancement (LE) process and trains the predictive model iteratively in every epoch. Specifically, we assume the true posterior density of the latent label distribution takes on the variational approximate Dirichlet density parameterized by an inference model. Then the evidence lower bound is deduced for optimizing the inference model and the label distributions generated from the variational posterior are utilized for training the predictive model. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed method. Source code is available at https://github.com/palm-ml/valen.
Exploiting Conjugate Label Information for Multi-Instance Partial-Label Learning
School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Key Lab. of Computer Network and Information Integration (Southeast University), MoE, China(教育部计算机网络与信息集成重点实验室(东南大学));School of Information and Physical Sciences, The University of Newcastle(纽卡斯尔大学信息与物理科学学院)
Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling
Key Laboratory of Data Engineering and Visual Computing, Chongqing University of Posts and Telecommunications, China(数据工程与视觉计算重点实验室,重庆邮电大学,中国);School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, China(计算机科学与技术学院,重庆邮电大学,中国);State Key Laboratory of Novel Software Technology, Nanjing University, China(新型软件技术国家重点实验室,南京大学,中国);School of Informatics, Aristotle University of Thessaloniki, Greece(信息学院,希腊阿尔蒂米斯大学)
Pseudo Labels Regularization for Imbalanced Partial-Label Learning
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);NLPR, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所模式识别国家重点实验室)
Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model
Nanjing University of Science and Technology(南京理工大学);Hong Kong Baptist University(香港浸会大学);The University of Sydney(悉尼大学);RIKEN Center for Advanced Intelligence Project (AIP)(理化学研究所先进智能项目中心(AIP));Hong Kong Polytechnic University(香港理工大学)
College of Software Engineering, Southeast University(东南大学软件学院);School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院);Yam Pak Charitable Foundation School of Computing and Information Sciences, Saint Francis University(圣弗朗西斯大学叶荫堂计算与信息科学学院);Department of Computer Science, City University of Hong Kong(香港城市大学计算机科学系)
Instance Correction for Learning with Open-set Noisy Labels
The University of Sydney(悉尼大学);Hong Kong Baptist University(香港浸会大学);The University of Melbourne(墨尔本大学);University of Science and Technology of China(中国科学技术大学);RIKEN(理化学研究所);The University of Tokyo(东京大学)
Non-I.I.D. Multi-Instance Learning for Predicting Instance and Bag Labels using Variational Auto-Encoder
多示例学习是一种弱监督学习。它处理数据是一组袋子的任务,每个袋子是一组实例。仅观察到袋标签,而实例的标签未知。多实例学习的一个重要优点是,通过将对象表示为一组实例,它能够保持对象各部分之间的固有依赖关系。不幸的是,大多数现有的算法假设所有实例都是\textit{identically and independently distributed},这违反了现实世界的场景,因为包中的实例很少是独立的。在这项工作中,我们提出了多实例变分自动编码器(MIVAE)算法,该算法显式地建模预测袋标签和实例标签的实例之间的依赖关系。在多个多实例基准测试和端到端医学成像数据集上的实验结果表明,MIVAE在实例标签和袋子标签预测任务上的表现优于最先进的算法。
Part-dependent Label Noise: Towards Instance-dependent Label Noise
University of Sydney(悉尼大学);Xidian University(西安电子科技大学);Hong Kong Baptist University(香港浸会大学);University of Melbourne(墨尔本大学);Brain-Inspired Technology Co., Ltd(脑启科技有限公司);RIKEN(理化学研究所);University of Tokyo(东京大学)
EchoAlign: Bridging Generative and Discriminative Learning under Noisy Labels
School of Software, Shandong University, Jinan 250100, China(山东大学软件学院,济南250100,中国);Sydney AI Centre, The University of Sydney, Sydney, NSW 2050, Australia(悉尼大学悉尼人工智能中心,悉尼,新南威尔士州2050,澳大利亚)
Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
School of Computer Science and Engineering, Southeast University(计算机科学与工程学院,东南大学);Key Laboratory of Computer Network and Information Integration (Southeast University), MoE, China(计算机网络与信息集成重点实验室(东南大学),教育部,中国);School of Information and Physical Sciences, The University of Newcastle(信息与物理科学学院,新castle大学)
Confidence Scores Make Instance-dependent Label-noise Learning Possible
RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心);Hong Kong Baptist University(香港浸会大学);University of Sydney(悉尼大学);University of Tokyo(东京大学)
Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimation
Xidian University(西安电子科技大学);The University of Sydney(悉尼大学);Hong Kong Baptist University(香港浸会大学);RIKEN(理化学研究所);Chongqing University of Posts and Telecommunications(重庆邮电大学);The University of Tokyo(东京大学)
Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
The Chinese University of Hong Kong(香港中文大学);VIVO AI Lab(vivo人工智能实验室);Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院)
Learning with Partial Labels from Semi-supervised Perspective
College of Computer Science and Technology, Jilin University(吉林大学计算机科学与技术学院);Key Laboratory of Symbolic Computation and Knowledge Engineering of MOE, Jilin University(吉林大学符号计算与知识工程教育部重点实验室);College of Information Science and Technology, Northeast Normal University(东北师范大学信息科学与技术学院);Key Laboratory of Applied Statistics of MOE, Northeast Normal University(东北师范大学应用统计教育部重点实验室)
Multi-View Multi-Instance Multi-Label Learning based on Collaborative Matrix Factorization
Southwest University(西南大学);China University of Geosciences(中国地质大学);George Mason University(乔治梅森大学);Deakin University(迪肯大学);Beijing University of Civil Engineering and Architecture(北京建筑大学)
Instance-dependent Label-noise Learning under a Structural Causal Model
University of Sydney(悉尼大学);University of Melbourne(墨尔本大学);Hong Kong Baptist University(香港浸会大学);RIKEN AIP(理化学研究所先进智能项目中心);Carnegie Mellon University(卡内基梅隆大学)
Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning
School of Computer Science and Technology, Xi’an Jiaotong University(西安交通大学计算机科学与技术学院);Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, Xi’an Jiaotong University(陕西省大数据知识工程重点实验室);School of Distance Education, Xi’an Jiaotong University(西安交通大学继续教育学院)