Information Sciences最新文献

筛选
英文 中文
Coarse-to-fine label refinement for domain adaptive retrieval 面向领域自适应检索的从粗到细标签细化
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-25 DOI: 10.1016/j.ins.2025.122532
Tianle Hu , Yu Chen , Chuwei Cheng , Junhong Xiao , Weijun Sun , Xiaozhao Fang
{"title":"Coarse-to-fine label refinement for domain adaptive retrieval","authors":"Tianle Hu ,&nbsp;Yu Chen ,&nbsp;Chuwei Cheng ,&nbsp;Junhong Xiao ,&nbsp;Weijun Sun ,&nbsp;Xiaozhao Fang","doi":"10.1016/j.ins.2025.122532","DOIUrl":"10.1016/j.ins.2025.122532","url":null,"abstract":"<div><div>Domain adaptive retrieval (DAR) is a promising research field. However, existing methods still suffer from the following limitations: 1) they rely heavily on pseudo-labeling strategies that oversimplify complex relationships between samples; 2) they treat labels as algorithmic outputs rather than optimizable variables, potentially breaking some natural connections between features and categories. To address these issues, we propose an effective approach called Coarse-to-Fine Label Refinement (CFLR). First, joint orthogonal matrix factorization is employed: one is to learn an optimizable latent feature representation, the other is to decompose predefined coarse pseudo-labels into improvable continuous values. Second, a classifier is introduced to connect these components, establishing a mutually reinforcing relationship between features and labels. This mutual enhancement captures implicit cross-category semantics by mining the iteratively updated feature information. Based on the refined labels, we develop an improved graph embedding that achieves more natural cross-domain relationships. Finally, high-quality hash codes are generated by directly quantifying the refined semantics. Experiments on multiple popular cross-domain benchmark datasets demonstrate that the proposed CFLR achieves state-of-the-art performance.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122532"},"PeriodicalIF":8.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Graph-constrained quantile regression: Unifying structured regularization and robust modeling for enhanced accuracy and interpretability 图约束分位数回归:统一结构化正则化和鲁棒建模,以提高准确性和可解释性
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-25 DOI: 10.1016/j.ins.2025.122530
Yao Dong , He Jiang , Sheng Pan , Jianzhou Wang
{"title":"Graph-constrained quantile regression: Unifying structured regularization and robust modeling for enhanced accuracy and interpretability","authors":"Yao Dong ,&nbsp;He Jiang ,&nbsp;Sheng Pan ,&nbsp;Jianzhou Wang","doi":"10.1016/j.ins.2025.122530","DOIUrl":"10.1016/j.ins.2025.122530","url":null,"abstract":"<div><div>Quantile regression has gained substantial popularity in the forecasting domain due to its flexibility in accommodating arbitrary response variable distributions. However, existing models predominantly rely on regularized approaches like the quantile least absolute shrinkage and selection operator (quantile LASSO), ignoring the critical role of spatial geometric structures play in enhancing prediction accuracy. This study proposes a novel forecasting model that integrates quantile regression with graphical regularization to exploit structural dependencies among predictors. The proposed model obtains both robustness and graphical structure among the predictors. The graphical regularization framework enables simultaneous predictor selection and exploitation of their correlations, leveraging graph-based penalties to capture geometric patterns. To efficiently solve the regularized optimization problem, we develop a proximal alternating direction method of multipliers (PADMM) algorithm, and theoretically prove its convergence. In empirical study, we consider several datasets to demonstrate the superior forecasting performance via comparing with other state-of-the-art statistical and deep learning models. The Freidman test is also provided to support our finding statistically.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122530"},"PeriodicalIF":8.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A graph regularized overlapping community discovery framework with three-way decisions 一个具有三向决策的图形正则化重叠社区发现框架
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-25 DOI: 10.1016/j.ins.2025.122525
Xiaoyang Zou , Jinxin Cao , Hengrong Ju , Weiping Ding , Lu Liu , Fuxiang Chen , Di Jin
{"title":"A graph regularized overlapping community discovery framework with three-way decisions","authors":"Xiaoyang Zou ,&nbsp;Jinxin Cao ,&nbsp;Hengrong Ju ,&nbsp;Weiping Ding ,&nbsp;Lu Liu ,&nbsp;Fuxiang Chen ,&nbsp;Di Jin","doi":"10.1016/j.ins.2025.122525","DOIUrl":"10.1016/j.ins.2025.122525","url":null,"abstract":"<div><div>Community detection is essential for complex network analysis. Most existing approaches focus on hard community partitioning, and a few have investigated overlapping community structures, which are important but difficult to handle in practical applications. This paper presents a graph regularization-based framework for overlapping community detection, which integrates topological information and applies a theoretical three-way decision method to handle uncertain knowledge. The proposed models, <span><math><mrow><mtext>GNMFO</mtext><mi>_</mi><mtext>TW</mtext></mrow></math></span>, <span><math><mrow><mtext>GYNMFO</mtext><mi>_</mi><mtext>TW</mtext></mrow></math></span>, and <span><math><mrow><mtext>GAEO</mtext><mi>_</mi><mtext>TW</mtext></mrow></math></span>, employ NMF, YNMF, and AEs with graph regularization terms for initial partitioning. The membership degrees of each node across different communities are then used for re-partitioning through three-way decisions. These models apply subspace clustering principles to incorporate basic network structure. To address the limitations caused by sparse network topology, the graph regularization terms encourage similar community membership among connected or nearby nodes, resulting in more coherent communities. In addition, three-way decisions, guided by node structural similarity, detect overlapping clusters and participating vertices. The proposed models not only identify community memberships but also reveal the overlapping community structures within networks. Empirical evaluations across both artificial and empirical networks indicate that our method outperforms existing advanced overlapping community detection techniques.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122525"},"PeriodicalIF":8.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A novel stock trading strategy based on double deep Q-network with sentiment integration 基于情感集成的双深度q网络股票交易策略
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-24 DOI: 10.1016/j.ins.2025.122541
Xiwen Qin , Jiawei Shen , Dingxin Xu , Siqi Zhang
{"title":"A novel stock trading strategy based on double deep Q-network with sentiment integration","authors":"Xiwen Qin ,&nbsp;Jiawei Shen ,&nbsp;Dingxin Xu ,&nbsp;Siqi Zhang","doi":"10.1016/j.ins.2025.122541","DOIUrl":"10.1016/j.ins.2025.122541","url":null,"abstract":"<div><div>Reinforcement learning (RL) has gained significant attention in stock trading strategies. However, existing RL models still show shortcomings. On the one hand, they fail to adequately account for the complex factors in real-world markets; on the other hand, they struggle to accurately capture the dynamic nature of financial markets, resulting in limited drawdown control and suboptimal returns. To address these challenges, we propose a novel stock trading strategy based on a Double Deep Q-Network (DDQN) with sentiment integration. First, sentiment features extracted from social media are combined with technical indicators to enhance the model’s understanding of market dynamics. Subsequently, trading decisions are made using the DDQN framework, which learns optimal policies through interaction with the market environment. To enhance performance, we adopt a Convolutional Neural Network − Bidirectional Gated Recurrent Unit (CNN–BiGRU) architecture as the Q-network, where CNN extracts local price patterns for short-term fluctuations, while BiGRU models temporal dependencies to capture long-term trends. Finally, trading signals from the RL process serve as labels to train multiple supervised classifiers. Experiments show that the proposed framework surpasses baseline models in major performance metrics including return, payoff ratio, and Sharpe ratio. This approach aims to provide accurate trading decision support for investors.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122541"},"PeriodicalIF":8.1,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Minimal Algorithmic Information Loss Methods for Dimension Reduction, Feature Selection and Network Sparsification 面向降维、特征选择和网络稀疏化的最小算法信息损失方法
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-24 DOI: 10.1016/j.ins.2025.122520
Hector Zenil , Narsis A. Kiani , Alyssa Adams , Felipe S. Abrahão , Antonio Rueda-Toicen , Allan A. Zea , Luan Ozelim , Jesper Tegnér
{"title":"Minimal Algorithmic Information Loss Methods for Dimension Reduction, Feature Selection and Network Sparsification","authors":"Hector Zenil ,&nbsp;Narsis A. Kiani ,&nbsp;Alyssa Adams ,&nbsp;Felipe S. Abrahão ,&nbsp;Antonio Rueda-Toicen ,&nbsp;Allan A. Zea ,&nbsp;Luan Ozelim ,&nbsp;Jesper Tegnér","doi":"10.1016/j.ins.2025.122520","DOIUrl":"10.1016/j.ins.2025.122520","url":null,"abstract":"<div><div>We present a novel, domain-agnostic, model-independent, unsupervised, and universally applicable Machine Learning approach for dimensionality reduction based on the principles of algorithmic complexity. Specifically, but without loss of generality, we focus on addressing the challenge of reducing certain dimensionality aspects, such as the number of edges in a network, while retaining essential features of interest. These features include preserving crucial network properties like degree distribution, clustering coefficient, edge betweenness, and degree and eigenvector centralities but can also go beyond edges to nodes and weights for network pruning and trimming. Our approach outperforms classical statistical Machine Learning techniques and state-of-the-art dimensionality reduction algorithms by preserving a greater number of data features that statistical algorithms would miss, particularly nonlinear patterns stemming from deterministic recursive processes that may look statistically random but are not. Moreover, previous approaches heavily rely on a priori feature selection, which requires constant supervision. Our findings demonstrate the effectiveness of the algorithms in overcoming some of these limitations while maintaining a time-efficient computational profile. Our approach not only matches, but also exceeds, the performance of established and state-of-the-art dimensionality reduction algorithms. We extend the applicability of our method to lossy compression tasks involving images and any multi-dimensional data. This highlights the versatility and broad utility of the approach in multiple domains.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122520"},"PeriodicalIF":8.1,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Power load forecasting using deep learning and reinforcement learning 利用深度学习和强化学习进行电力负荷预测
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-24 DOI: 10.1016/j.ins.2025.122523
Yao Dong , Kai Liu , He Jiang , Yawei Dong , Jianzhou Wang
{"title":"Power load forecasting using deep learning and reinforcement learning","authors":"Yao Dong ,&nbsp;Kai Liu ,&nbsp;He Jiang ,&nbsp;Yawei Dong ,&nbsp;Jianzhou Wang","doi":"10.1016/j.ins.2025.122523","DOIUrl":"10.1016/j.ins.2025.122523","url":null,"abstract":"<div><div>Accurate power load forecasting plays a pivotal role in balancing power supply and demand within smart grid development. While hybrid forecasting technologies have gained popularity in power load forecast, existing forecasting modules often rely on traditional models such as statistical methods, machine learning, and long short-term memory (LSTM), which limits their diverse applications. To resolve this challenge, we develop a novel multi-factor and multi-scale power load forecasting method. The proposed method comprises three steps: firstly, power loads and meteorological factors are decomposed using the noise-assisted multivariate variational mode decomposition (NA-MVMD) method across multiple scales, capturing temporal characteristics. Next, individual forecast is generated for each decomposition using the adaptive Nesterov momentum algorithm (Adan) and inverted transformer (iTransformer). Finally, the weights corresponding to each prediction result are determined using the Dueling Deep Q-Network reinforcement learning method, and the results are aggregated by weighted summation. The empirical study using the New York City dataset demonstrates that the proposed model achieves robust stability and high forecast accuracy comparing with other competitors. These findings reveal its potential to inform smart grid optimization strategies effectively.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122523"},"PeriodicalIF":8.1,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
ICAM: An interpretable auxiliary model for the pathological diagnosis of breast cancer based on knowledge embedding 基于知识嵌入的可解释乳腺癌病理诊断辅助模型
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-24 DOI: 10.1016/j.ins.2025.122521
Lihua Gu , Xiaomin Xiong , Qun Liu , Dajiang Lei , Ruqi Wang , Bo Lin , Guoyin Wang , Bo Xu
{"title":"ICAM: An interpretable auxiliary model for the pathological diagnosis of breast cancer based on knowledge embedding","authors":"Lihua Gu ,&nbsp;Xiaomin Xiong ,&nbsp;Qun Liu ,&nbsp;Dajiang Lei ,&nbsp;Ruqi Wang ,&nbsp;Bo Lin ,&nbsp;Guoyin Wang ,&nbsp;Bo Xu","doi":"10.1016/j.ins.2025.122521","DOIUrl":"10.1016/j.ins.2025.122521","url":null,"abstract":"<div><div>Pathological diagnosis is the gold standard for cancer diagnosis. To provide reliable pathological diagnoses, this study proposes a pathological image diagnostic model based on knowledge embeddings. The model effectively guides the learning of pathological diagnostic features by embedding domain knowledge, thereby improving its efficiency. On this basis, nonnegative matrix factorization (NMF) is applied locally. As a powerful feature decomposition method, NMF can effectively extract local patterns and texture information from images, enhancing the capability of representing features and further strengthening the model's ability to capture key features. Finally, the decision basis of the model is derived through backward deduction of the model's computational steps, providing clear diagnostic reasoning for clinical doctors. The validation results on both private and public datasets show that, compared with conventional models, the proposed approach improves the accuracy (ACC) by 15.8% and the F1 score by 15.4%. The comparison with other methods highlights the robustness of ICAM and underscores its potential advantages over other transformer-based approaches. Additionally, the model's decision-making rationale is revealed through clear visual explanations, which are consistent with clinical observations, demonstrating its practical utility and clinical reference value.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122521"},"PeriodicalIF":8.1,"publicationDate":"2025-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CSC-DARTS: Efficient differentiable neural architecture search using channel splitting connections 使用通道分裂连接的高效可微神经结构搜索
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-23 DOI: 10.1016/j.ins.2025.122538
Hui Wei , Feifei Lee , Lin Xie , Li Liu , Hongliu Yu , Qiu Chen
{"title":"CSC-DARTS: Efficient differentiable neural architecture search using channel splitting connections","authors":"Hui Wei ,&nbsp;Feifei Lee ,&nbsp;Lin Xie ,&nbsp;Li Liu ,&nbsp;Hongliu Yu ,&nbsp;Qiu Chen","doi":"10.1016/j.ins.2025.122538","DOIUrl":"10.1016/j.ins.2025.122538","url":null,"abstract":"<div><div>Recently, differentiable architecture search (DARTS) has made great progress in decreasing the computational cost of Neural Architecture Search (NAS). However, there is still a problem of excessive memory access costs in training the supernet. In this paper, we propose an efficient search framework for differentiable architecture search using channel splitting connections, namely CSC-DARTS, based on bi-level optimization and second-order gradient approximation. Specifically, a “Channel Splitting” technique is developed to split the feature maps of the supernet at the channel level into two branches, one of which is sent to the operation selection for less redundancy when exploring the search space, while bypassing the rest directly to the output as feature reuse. In addition, an “identity” connection is adopted in both the search and evaluation phases, which is regarded as a regularization for less variability, to bridge a large gap caused by the inconsistency of the architecture depth between the two stages. Experimental results on the benchmark datasets CIFAR-10, CIFAR-100, and ImageNet demonstrate that CSC-DARTS achieves state-of-the-art performance with fewer GPU resources, including a test error of 2.52 % on CIFAR-10, an average test error of 17.25 % on CIFAR-100, and a top-1/5 accuracy of 74.5 %/91.7 % on ImageNet.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122538"},"PeriodicalIF":8.1,"publicationDate":"2025-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144703722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Sequence value decomposition transformer for cooperative multi-agent reinforcement learning 协同多智能体强化学习的序列值分解转换器
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-22 DOI: 10.1016/j.ins.2025.122514
Zhitong Zhao , Ya Zhang , Wenyu Chen , Fan Zhang , Siying Wang , Yang Zhou
{"title":"Sequence value decomposition transformer for cooperative multi-agent reinforcement learning","authors":"Zhitong Zhao ,&nbsp;Ya Zhang ,&nbsp;Wenyu Chen ,&nbsp;Fan Zhang ,&nbsp;Siying Wang ,&nbsp;Yang Zhou","doi":"10.1016/j.ins.2025.122514","DOIUrl":"10.1016/j.ins.2025.122514","url":null,"abstract":"<div><div>Existing multi-agent reinforcement learning (MARL) methods that utilize the centralized training with decentralized execution (CTDE) paradigm have achieved great empirical success in cooperative tasks. However, the CTDE paradigm struggles to capture the unequal interactions of agents by evaluating the joint actions simultaneously. In this paper, we introduce the concept of action sequences, which consider the unequal interactions among agents from multiple perspectives through different action orderings. Subsequently, we propose the multi-agent sequence value decomposition, allowing for a more comprehensive estimation of the joint q-value function through action sequences. Building on this, we construct a value decomposition transformer (VDT) framework to implement the multi-agent sequence value decomposition within the CTDE paradigm. By utilizing the transformer network, the VDT framework completes the centralized training with action sequences, resulting in enhancing cooperation capability in coordinated learning. Extensive experiments on the predator-prey task and the StarCraft multi-agent challenge demonstrate that our proposed VDT framework achieves significantly improved learning speed and cooperative performance. Compared to the state-of-the-art methods, VDT exhibits significant improvement in learning efficiency within the same timesteps and achieves an average 20% enhancement within the final cooperative performance.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122514"},"PeriodicalIF":8.1,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A multi-view forward positive and unlabeled graph learning method based on dictionary learning 一种基于字典学习的多视图正向正无标记图学习方法
IF 8.1 1区 计算机科学
Information Sciences Pub Date : 2025-07-22 DOI: 10.1016/j.ins.2025.122517
Bo Liu , Chenlong Ye , Yanshan Xiao , Baoqing Li , Zhitong Wang , Boxu Zhou , Shengxin He , Fan Cao
{"title":"A multi-view forward positive and unlabeled graph learning method based on dictionary learning","authors":"Bo Liu ,&nbsp;Chenlong Ye ,&nbsp;Yanshan Xiao ,&nbsp;Baoqing Li ,&nbsp;Zhitong Wang ,&nbsp;Boxu Zhou ,&nbsp;Shengxin He ,&nbsp;Fan Cao","doi":"10.1016/j.ins.2025.122517","DOIUrl":"10.1016/j.ins.2025.122517","url":null,"abstract":"<div><div>With the increasing demand for graph data analysis in complex real-world scenarios, traditional graph classification methods that rely solely on labeled positive/negative samples face significant limitations due to data scarcity. To address this challenge, we propose a novel multi-view positive and unlabeled graph learning framework based on dictionary learning (MVPU-DL). Our approach innovatively utilizes unlabeled graphs as privileged information through three key mechanisms: 1) a multi-view dictionary learning paradigm with cross-view consistency constraints, which uses analytical dictionaries to generate discriminative sparse codes; 2) a novel PU-SVM classifier architecture that integrates view-specific dictionaries to enable robust feature representation from limited positive samples; 3) an alternating convex optimization strategy with provable convergence for jointly learning discriminative dictionaries and classification boundaries. Extensive experiments on 12 benchmark datasets spanning diverse domains—including biological compounds (PTC, MUTAG), chemical interactions (COX2, DHFR), and social networks (Twitter, DBLP)—validate the superior performance of MVPU-DL. The proposed cross-view dictionary alignment strategy is particularly effective under varying labeling ratios, achieving a significant average F1-score improvement of 2.16% (with a maximum improvement of 3.88%) compared to state-of-the-art baselines. These results demonstrate that MVPU-DL outperforms other methods with remarkable performance.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"720 ","pages":"Article 122517"},"PeriodicalIF":8.1,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信