相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Wenbin Qian et al.
Summary: This paper proposes a disambiguation-based partial label feature selection algorithm using granular ball computing and neighborhood rough sets to evaluate the importance of each feature. Experiments demonstrate that the proposed algorithm can improve the generalization performance of partial label learning.
INFORMATION FUSION
(2023)
Article
Computer Science, Artificial Intelligence
Kun Qian et al.
Summary: In this paper, we propose a 2SML algorithm that uses a shared weight matrix with low-rank and sparse regularization to address the issues of sparse labels, missing labels, and sparse structures in multi-label learning. Experimental results show that the proposed method outperforms the state-of-the-art methods on multiple benchmark datasets.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Information Systems
Lijuan Sun et al.
Summary: This paper proposes a novel approach called Global-Local Label Correlation (GLC) for partial multi-label learning. By leveraging both global and local label correlations, the proposed method achieves superior performance on synthetic and real-world datasets.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Information Systems
Jin Ye et al.
Summary: This paper introduces a new 3WD model applied to realistic MCDM problems and discusses related issues in a fuzzy probabilistic rough set model through a decision information system. A novel approach is established for classifying and ranking applicants for enterprise talent recruitment problems, with the feasibility of the method confirmed. Experimental results demonstrate the better performance in terms of effectiveness and stability of the constructed MCDM approach.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Xin Yang et al.
Summary: In this paper, a novel framework of sequential three-way decision for the fusion of mixed data from the subjective and objective dynamic perspectives is explored. The proposed models achieve lower decision cost and acceptable accuracy, as demonstrated by comparative experiments.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yiyu Yao et al.
Summary: This paper introduces the concept of Pawlak approximation space, explores the impact of the two-space view on rough set theory, proposes the notions of granular rough sets and probabilistic granular rough sets in the quotient space, and discusses the construction method and properties of granular shadowed sets.
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING
(2022)
Article
Computer Science, Artificial Intelligence
Wenbin Qian et al.
Summary: This paper presents a label enhancement-based feature selection method for addressing the challenges of high dimensionality and multiple semantics in multi-label classification. Experimental results demonstrate the superior performance of this method across multiple evaluation indicators.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Peng Zhao et al.
Summary: In many real-world applications, instances from the training dataset often have irrelevant labels, which cannot be handled well by traditional multi-label learning methods. This motivates the development of partial multi-label learning. Existing methods usually ignore the fact that label correlations can be corrupted by noisy labels and assume label correlations to be symmetric. To address these issues, this paper proposes a partial multi-label learning method based on sparse asymmetric label correlations. The experimental results demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Information Systems
Haibo Jiang et al.
Summary: This paper proposes an evaluation-based interval-valued multi-attribute three-way decision (IVMA3WD) model, which combines three-way decisions and multi-attribute decision-making problems, and models uncertain information using interval numbers, achieving the handling of uncertain information and automatic provision of decision priority objects.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Linchao Pan et al.
Summary: The study presents a TWD-based tri-training model for handling partially labeled data with heterogeneous attributes. Through semi-supervised reduction and multi-view training, the proposed model effectively handles partially labeled data and demonstrates better performance than supervised models in experiments.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Wenbin Qian et al.
Summary: This paper proposes a cost-sensitive sequential three-way decision model for information systems with fuzzy decision, which achieves better classification performance and lower test costs by optimizing information granularity.
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING
(2022)
Article
Computer Science, Artificial Intelligence
Xiao-Hong Pan et al.
Summary: This paper proposes a novel interval-valued TWD theory for solving MCDM problems under uncertain environment. It introduces a new approach to calculate the interval-valued conditional probability of each alternative and establishes a new information transformation and fusion mechanism to conduct the interval-valued thresholds under multiple criteria into overall interval-valued thresholds. The effectiveness and superiority of the proposed method are demonstrated through an application example and comparisons with other methods.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Xiao-Hong Pan et al.
Summary: The novel interval-valued TWD theory proposed in this paper addresses multiple criteria decision-making problems under uncertain environments. By defining rules, calculating conditional probabilities, and providing decision rules, the interval-valued thresholds under multiple criteria are transformed into overall interval-valued thresholds for generating classifications and rankings of alternatives.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Guangyi Lin et al.
Summary: Partial label learning (PLL) is a type of weak supervision learning problem where each data sample has multiple candidate labels. The PL-PIE algorithm proposed in this paper uses prior label distribution information to achieve stable performance. Experimental results show that PL-PIE has competitive performance compared to other state-of-the-art PLL algorithms.
Article
Computer Science, Information Systems
Gengyu Lyu et al.
Summary: Partial Multi-Label learning faces challenges from label noise, with existing methods focusing on label disambiguation potentially leading to misidentification of remaining credible labels. The proposed Natal method addresses this issue by treating labeling information as precise and completing missing features, effectively reinterpreting PML as a feature completion problem. Extensive experiments show the effectiveness of this approach.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Yan Yan et al.
Summary: The proposed PML-MT model utilizes self-ensemble teacher networks to iteratively refine the label confidence matrix and trains two prediction networks simultaneously in a mutual teaching manner. Additionally, a novel regularization term is introduced to exploit label correlations and maximize the agreement on the outputs of the couple prediction networks, leading to more reliable predictions.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Min-Ling Zhang et al.
Summary: Partial multi-label learning aims to induce a multi-label predictor by handling the issue of each training example being associated with an overcomplete set of candidate labels, in order to improve generalization performance.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Review
Computer Science, Artificial Intelligence
Adane Nega Tarekegn et al.
Summary: Multi-Label Classification (MLC) is an extension of standard single-label classification where each data instance is associated with several labels. The class imbalance problem has become inherent in many MLC datasets, posing challenges to multi-label data analysis.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Information Systems
Lin Sun et al.
INFORMATION SCIENCES
(2020)
Article
Automation & Control Systems
Chen Gong et al.
IEEE TRANSACTIONS ON CYBERNETICS
(2018)
Article
Computer Science, Artificial Intelligence
Min-Ling Zhang et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2017)
Review
Computer Science, Artificial Intelligence
Min-Ling Zhang et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2014)
Article
Computer Science, Information Systems
Yiyu Yao
INFORMATION SCIENCES
(2011)
Article
Computer Science, Artificial Intelligence
Jesse Read et al.
Article
Computer Science, Information Systems
Yiyu Yao
INFORMATION SCIENCES
(2010)
Article
Computer Science, Artificial Intelligence
Weiwei Cheng et al.
Article
Computer Science, Artificial Intelligence
Min-Ling Zhang
NEURAL PROCESSING LETTERS
(2009)
Article
Computer Science, Artificial Intelligence
Johannes Fuernkranz et al.
Article
Computer Science, Artificial Intelligence
Min-Ling Zhang et al.
PATTERN RECOGNITION
(2007)
Article
Computer Science, Artificial Intelligence
Min-Ling Zhang et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2006)
Article
Computer Science, Artificial Intelligence
Eyke Huellermeier et al.
INTELLIGENT DATA ANALYSIS
(2006)
Article
Computer Science, Artificial Intelligence
ZH Zhou et al.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2005)
Article
Computer Science, Artificial Intelligence
MR Boutell et al.
PATTERN RECOGNITION
(2004)