Article
Computer Science, Artificial Intelligence
Yikai Zhang, Yong Peng, Hongyu Bian, Yuan Ge, Feiwei Qin, Wanzeng Kong
Summary: The paper introduces the Auto-Weighted Concept Factorization (AWCF) model, which adaptsively learns the contributions of different features by introducing an auto-weighting variable, leading to more effective data representation and better measurement of feature importance. The results of experiments on synthetic and representative benchmark data sets show the effectiveness of AWCF in comparison with some related models.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Zhen Wang, Shan-Shan Wang, Lan Bai, Wen-Si Wang, Yuan-Hai Shao
Summary: This article proposes a semisupervised fuzzy clustering method with fuzzy pairwise constraints, which can represent more complex relationships between samples and avoid eliminating fuzzy characteristics. The method solves a nonconvex optimization problem using a modified expectation-maximization algorithm and diagonal block coordinate descent algorithm, and is extended to different metric spaces. Experimental results demonstrate the superior performance of this method.
IEEE TRANSACTIONS ON FUZZY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Chenyu Shao, Mulin Chen, Qi Wang, Yuan Yuan
Summary: This paper discusses the application of matrix factorization-based techniques in data analysis. By constructing a similarity graph and using a concept factorization model, it is possible to capture both local and global structures, and by introducing a projection matrix, the noise can be eliminated and the out-of-sample problem can be avoided.
Article
Computer Science, Artificial Intelligence
Yecheng Guo, Liang Bai, Xian Yang, Jiye Liang
Summary: This article introduces a new unsupervised clustering model, which improves clustering results for images by integrating pairwise constraints into the clustering process. The model autonomously learns pairwise constraints, eliminating the need for labeled images and offering a practical solution to the challenge of insufficient supervised information in unsupervised clustering tasks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Weizhong Yu, Liyin Xing, Feiping Nie, Xuelong Li
Summary: Semi supervised clustering algorithms with limited prior information have attracted attention recently. Graph-based algorithms have been proposed due to their natural suitability for pairwise constraints. However, most graph-based approaches have high time complexity and suffer from constraint violation. In this paper, we propose a new non-parametric model that can directly obtain the indicator matrix and handle constraint violation in an efficient and effective way.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Ying Zhang, Xiangli Li, Mengxue Jia
Summary: Traditional clustering is an unsupervised learning method, but prior information in actual data can be used for semi-supervised clustering. Pairwise constraints are commonly used prior information that can improve clustering performance. This paper proposes a semi-supervised clustering method that combines pairwise constraints with nonnegative matrix factorization and verifies its effectiveness through experiments.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2022)
Article
Chemistry, Multidisciplinary
Yalin Wang, Jiangfeng Zou, Kai Wang, Chenliang Liu, Xiaofeng Yuan
Summary: Semi-supervised deep clustering methods have received much attention for their impressive performance in end-to-end clustering task. However, obtaining satisfactory clustering results is challenging due to the strong and incorrect influence of overlapping samples in industrial text datasets. Existing methods incorporate prior knowledge using pairwise constraints or class labels, which often ignore the correlation between these two types of supervision information and lead to weak-supervised constraints or incorrect strong-supervised label guidance. To address these problems, we propose a novel semi-supervised method called PCSA-DEC based on pairwise constraints and subset allocation. Experimental results on two industrial text datasets demonstrate that our method achieves significant improvements in accuracy and normalized mutual information compared to the state-of-the-art method.
MENDELEEV COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Dexian Wang, Tianrui Li, Ping Deng, Hongjun Wang, Pengfei Zhang
Summary: This paper presents the Dual Graph-Regularized Sparse Concept Factorization (DGSCF) algorithm, which enhances clustering performance and eliminates the influence of noise factors through dual graph regularization and an optimization framework based on l(1) and Frobenius norms.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Mulin Chen, Xuelong Li
Summary: Data clustering is a fundamental machine learning problem, and the proposed concept factorization with local centroids (CFLCs) approach addresses the limitations of existing methods by allowing samples to connect with multiple local centroids for capturing manifold structures and providing a reasonable label assignment. Experimental results demonstrate the superior performance of the CFLC model over state-of-the-art techniques on various datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Shuai Chang, Jie Hu, Tianrui Li, Hao Wang, Bo Peng
Summary: Recent studies have shown the satisfactory results of deep matrix factorization clustering models in Multi-view Clustering. In this paper, a novel MVC model is proposed to integrate deep Concept Factorization into MVC and learn hierarchical information through multi-layer CF. Experiment results demonstrate the superior performance of the proposed model compared with baseline methods.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Siyuan Peng, Zhijing Yang, Bingo Wing-Kuen Ling, Badong Chen, Zhiping Lin
Summary: A new semi-supervised NMF method called dual semi-supervised convex nonnegative matrix factorization (DCNMF) is proposed in this paper. DCNMF incorporates the pointwise and pairwise constraints of labeled samples into convex NMF, resulting in a better low-dimensional data representation. It can process mixed-sign data due to the nonnegative constraint only on the coefficient matrix.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Rui Chen, Yongqiang Tang, Wensheng Zhang, Wenlong Feng
Summary: In this paper, the authors propose a novel Deep Multi-view Semi-supervised Clustering (DMSC) method that optimizes multiple loss functions to improve clustering performance. The method incorporates a KL divergence based multi-view clustering loss, a semi-supervised pairwise constraint loss, and multiple autoencoders reconstruction loss, all of which are jointly optimized during network finetuning. Experimental results on eight popular image datasets demonstrate that the proposed method outperforms state-of-the-art multi-view and single-view competitors.
Article
Computer Science, Artificial Intelligence
Wenhui Wu, Junhui Hou, Shiqi Wang, Sam Kwong, Yu Zhou
Summary: In this paper, we propose a semi-supervised adaptive kernel concept factorization (SAKCF) method that integrates data representation and kernel learning and solves the problem using an alternating iterative algorithm. Experimental results demonstrate the effectiveness and advantages of SAKCF over other methods in clustering tasks.
PATTERN RECOGNITION
(2023)
Article
Mathematical & Computational Biology
Yaxin Xu, Wei Zhang, Xiaoying Zheng, Xianxian Cai
Summary: Single-cell RNA sequencing technology is an important method to study transcriptomic heterogeneity. However, accurately clustering the high-dimensional and noisy scRNA-seq data is a challenging task. In this study, a novel computational method called GCFG was developed to cluster scRNA-seq data by integrating global and local information. The effectiveness and robustness of GCFG were evaluated on real datasets and compared with other methods.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Sheng Wang, Liyong Chen, Yaowei Sun, Furong Peng, Jianfeng Lu
Summary: This paper proposes a novel method called multiview nonnegative matrix factorization with dual HSIC constraints for clustering, which utilizes multiple features for clustering. The method employs the Hilbert-Schmidt independence criterion (HSIC) to measure the correlation between the latent representation of each view and the common ones, and maximizes the independence among the vectors of the basis matrix for each view. To maintain the nonlinear structure of multiview data, the method directly optimizes the kernel of the common representation and constrains its values using partition entropy. The proposed algorithm is extensively tested and compared with state-of-the-art NMF-based multiview methods on four datasets, and the clustering results validate its effectiveness.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Hamdan Abdellatef, Lina J. Karam
Summary: This paper proposes performing the learning and inference processes in the compressed domain to reduce computational complexity and improve speed of neural networks. Experimental results show that modified ResNet-50 in the compressed domain is 70% faster than traditional spatial-based ResNet-50 while maintaining similar accuracy. Additionally, a preprocessing step with partial encoding is suggested to improve resilience to distortions caused by low-quality encoded images. Training a network with highly compressed data can achieve good classification accuracy with significantly reduced storage requirements.
Article
Computer Science, Artificial Intelligence
Victor R. Barradas, Yasuharu Koike, Nicolas Schweighofer
Summary: Inverse models are essential for human motor learning as they map desired actions to motor commands. The shape of the error surface and the distribution of targets in a task play a crucial role in determining the speed of learning.
Article
Computer Science, Artificial Intelligence
Ting Zhou, Hanshu Yan, Jingfeng Zhang, Lei Liu, Bo Han
Summary: We propose a defense strategy that reduces the success rate of data poisoning attacks in downstream tasks by pre-training a robust foundation model.
Article
Computer Science, Artificial Intelligence
Hao Sun, Li Shen, Qihuang Zhong, Liang Ding, Shixiang Chen, Jingwei Sun, Jing Li, Guangzhong Sun, Dacheng Tao
Summary: In this paper, the convergence rate of AdaSAM in the stochastic non-convex setting is analyzed. Theoretical proof shows that AdaSAM has a linear speedup property and decouples the stochastic gradient steps with the adaptive learning rate and perturbed gradient. Experimental results demonstrate that AdaSAM outperforms other optimizers in terms of performance.
Article
Computer Science, Artificial Intelligence
Juntong Yun, Du Jiang, Li Huang, Bo Tao, Shangchun Liao, Ying Liu, Xin Liu, Gongfa Li, Disi Chen, Baojia Chen
Summary: In this study, a dual manipulator grasping detection model based on the Markov decision process is proposed. By parameterizing the grasping detection model of dual manipulators using a cross entropy convolutional neural network and a full convolutional neural network, stable grasping of complex multiple objects is achieved. Robot grasping experiments were conducted to verify the feasibility and superiority of this method.
Article
Computer Science, Artificial Intelligence
Miaohui Zhang, Kaifang Li, Jianxin Ma, Xile Wang
Summary: This paper proposes an unsupervised person re-identification (Re-ID) method that uses two asymmetric networks to generate pseudo-labels for each other by clustering and updates and optimizes the pseudo-labels through alternate training. It also designs similarity compensation and similarity suppression based on the camera ID of pedestrian images to optimize the similarity measure. Extensive experiments show that the proposed method achieves superior performance compared to state-of-the-art unsupervised person re-identification methods.
Article
Computer Science, Artificial Intelligence
Florian Bacho, Dominique Chu
Summary: This paper proposes a new approach called the Forward Direct Feedback Alignment algorithm for supervised learning in deep neural networks. By combining activity-perturbed forward gradients, direct feedback alignment, and momentum, this method achieves better performance and convergence speed compared to other local alternatives to backpropagation.
Article
Computer Science, Artificial Intelligence
Xiaojian Ding, Yi Li, Shilin Chen
Summary: This research paper addresses the limitations of recursive feature elimination (RFE) and its variants in high-dimensional feature selection tasks. The proposed algorithms, which introduce a novel feature ranking criterion and an optimal feature subset evaluation algorithm, outperform current state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Naoko Koide-Majima, Shinji Nishimoto, Kei Majima
Summary: Visual images observed by humans can be reconstructed from brain activity, and the visualization of arbitrary natural images from mental imagery has been achieved through an improved method. This study provides a unique tool for directly investigating the subjective contents of the brain.
Article
Computer Science, Artificial Intelligence
Huanjie Tao, Qianyue Duan
Summary: In this paper, a hierarchical attention network with progressive feature fusion is proposed for facial expression recognition (FER), addressing the challenges posed by pose variation, occlusions, and illumination variation. The model achieves enhanced performance by aggregating diverse features and progressively enhancing discriminative features.
Article
Computer Science, Artificial Intelligence
Zhenyi Wang, Pengfei Yang, Linwei Hu, Bowen Zhang, Chengmin Lin, Wenkai Lv, Quan Wang
Summary: In the face of the complex landscape of deep learning, we propose a novel subgraph-level performance prediction method called SLAPP, which combines graph and operator features through an innovative graph neural network called EAGAT, providing accurate performance predictions. In addition, we introduce a mixed loss design with dynamic weight adjustment to improve predictive accuracy.
Article
Computer Science, Artificial Intelligence
Yiyang Yin, Shuangling Luo, Jun Zhou, Liang Kang, Calvin Yu-Chian Chen
Summary: Medical image segmentation is crucial for modern healthcare systems, especially in reducing surgical risks and planning treatments. Transanal total mesorectal excision (TaTME) has become an important method for treating colon and rectum cancers. Real-time instance segmentation during TaTME surgeries can assist surgeons in minimizing risks. However, the dynamic variations in TaTME images pose challenges for accurate instance segmentation.
Article
Computer Science, Artificial Intelligence
Teng Cheng, Lei Sun, Junning Zhang, Jinling Wang, Zhanyang Wei
Summary: This study proposes a scheme that combines the start-stop point signal features for wideband multi-signal detection, called Fast Spectrum-Size Self-Training network (FSSNet). By utilizing start-stop points to build the signal model, this method successfully solves the difficulty of existing deep learning methods in detecting discontinuous signals and achieves satisfactory detection speed.
Article
Computer Science, Artificial Intelligence
Wenming Wu, Xiaoke Ma, Quan Wang, Maoguo Gong, Quanxue Gao
Summary: The layer-specific modules in multi-layer networks are critical for understanding the structure and function of the system. However, existing methods fail to accurately characterize and balance the connectivity and specificity of these modules. To address this issue, a joint learning graph clustering algorithm (DRDF) is proposed, which learns the deep representation and discriminative features of the multi-layer network, and balances the connectivity and specificity of the layer-specific modules through joint learning.
Article
Computer Science, Artificial Intelligence
Guanghui Yue, Guibin Zhuo, Weiqing Yan, Tianwei Zhou, Chang Tang, Peng Yang, Tianfu Wang
Summary: This paper proposes a novel boundary uncertainty aware network (BUNet) for precise and robust colorectal polyp segmentation. BUNet utilizes a pyramid vision transformer encoder to learn multi-scale features and incorporates a boundary exploration module (BEM) and a boundary uncertainty aware module (BUM) to handle boundary areas. Experimental results demonstrate that BUNet outperforms other methods in terms of performance and generalization ability.