Information Sciences最新文献

{"title":"Robust partial 3D point cloud registration via confidence estimation under global context","authors":"Yongqiang Wang ,&nbsp;Weigang Li ,&nbsp;Wenping Liu ,&nbsp;Zhe Xu ,&nbsp;Zhiqiang Tian","doi":"10.1016/j.ins.2025.122705","DOIUrl":"10.1016/j.ins.2025.122705","url":null,"abstract":"<div><div>Partial point cloud registration is essential for autonomous perception and 3D scene understanding, yet it remains challenging owing to structural ambiguity, partial visibility, and noise. We address these issues by proposing Confidence Estimation under Global Context (CEGC), a unified, confidence-driven framework for robust partial 3D registration. CEGC enables accurate alignment in complex scenes by jointly modeling overlap confidence and correspondence reliability within a shared global context. Specifically, the hybrid overlap confidence estimation module integrates semantic descriptors and geometric similarity to detect overlapping regions and suppress outliers early. The context-aware matching strategy mitigates ambiguity by employing global attention to assign soft confidence scores to correspondences, improving robustness. These scores guide a differentiable weighted singular value decomposition solver to compute precise transformations. This tightly coupled pipeline adaptively down-weights uncertain regions and emphasizes contextually reliable matches. Experiments on ModelNet40, ScanObjectNN, and 7Scenes 3D vision datasets demonstrate that CEGC outperforms state-of-the-art methods in accuracy, robustness, and generalization. Overall, CEGC offers an interpretable and scalable solution to partial point cloud registration under challenging conditions.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122705"},"PeriodicalIF":6.8,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158880","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}

{"title":"Editorial: Combining machine learning and metaheuristics for optimizing complex intelligent systems","authors":"Jian Wang,&nbsp;Chanjuan Liu,&nbsp;Jacek Mańdziuk (Guest Editors)","doi":"10.1016/j.ins.2025.122707","DOIUrl":"10.1016/j.ins.2025.122707","url":null,"abstract":"","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"722 ","pages":"Article 122707"},"PeriodicalIF":6.8,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266939","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}

{"title":"FedWAPR: Bridging theory and practice in probability-driven weighted aggregation for federated learning","authors":"Abdullah Abdul Sattar Shaikh ,&nbsp;M.S. Bhargavi ,&nbsp;Pavan Kumar C","doi":"10.1016/j.ins.2025.122697","DOIUrl":"10.1016/j.ins.2025.122697","url":null,"abstract":"<div><div>Federated Learning (FL) is a machine learning paradigm emphasizing data privacy, widely adopted for handling sensitive data. Federated Averaging (FedAvg) is the most commonly implemented FL aggregation technique due to its simplicity and effectiveness. However, FedAvg suffers from information loss during the aggregation stage. This study theoretically and empirically analyzes the Weighted Aggregation via Probability-based Ranking (FedWAPR) technique, an enhancement to FedAvg that retains its simplicity while addressing its limitations. FedWAPR employs a weighted aggregation strategy based on Log-Cauchy and Exponential probability density functions, assigning weights to local models based on their performance. This approach ensures accurate aggregation that reflects the contributions of individual clients. FedWAPR was tested across various model architectures, including Dense Neural Networks, Long Short-Term Memory networks, and Convolutional Neural Networks with results showing performance equal to or surpassing FedAvg. The Log-Cauchy and Exponential distribution functions allow customization of aggregation based on the number of participating clients, with exponential distribution excelling in smaller client setups and Log-Cauchy in larger ones. FedWAPR’s ability to integrate with advanced aggregation techniques like FedProx, makes it a robust solution to enhance FL. Additionally, a theoretical analysis confirms the convergence of FedWAPR under standard FL assumptions and thereby ensuring method’s robustness and reliability.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122697"},"PeriodicalIF":6.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145158878","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}

{"title":"A novel approach for shortest optimal reduct computation","authors":"G.Y. Phani Kumar ,&nbsp;Abhimanyu Bar ,&nbsp;P.S.V.S. Sai Prasad","doi":"10.1016/j.ins.2025.122692","DOIUrl":"10.1016/j.ins.2025.122692","url":null,"abstract":"<div><div>Rough set theory has emerged as a robust soft computing paradigm for feature selection, commonly known as reduct computation. A decision system may contain multiple reducts of varying sizes, all offering equivalent classification capabilities. However, when model performance is a critical factor, the shortest reduct is generally preferred due to its simplicity and interpretability. The discernibility matrix method is a widely used technique for computing such reducts. Despite its effectiveness, this method is computationally intensive and classified as NP-hard, limiting its scalability for datasets where discernibility matrix computation becomes infeasible. This study addresses the limitations of traditional discernibility matrix-based approaches by introducing a novel method that combines a Breadth-First Search control strategy with an incremental approach to compute the absorbed discernibility matrix. The Breadth First Search strategy enables efficient exploration of the search space to identify the shortest optimal reduct early, while the incremental absorbed discernibility matrix enhances the computational scalability of the algorithm. To validate the proposed method, an experimental evaluation was conducted against two state-of-the-art algorithms: Breadth-First Search, representing the discernibility matrix-based strategy, and MinReduct, a benchmark for absorbed discernibility matrix-based approaches. Results demonstrate superior computational performance and earlier discovery of shortest reducts without compromising correctness or optimality.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122692"},"PeriodicalIF":6.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107117","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}

{"title":"Long- and short-term preferences modeling based on dual-frequency self-attention network for sequential recommendation","authors":"Kaiwei Xu ,&nbsp;Yongquan Fan ,&nbsp;Jing Tang ,&nbsp;Xianyong Li ,&nbsp;Yajun Du ,&nbsp;Xiaomin Wang","doi":"10.1016/j.ins.2025.122700","DOIUrl":"10.1016/j.ins.2025.122700","url":null,"abstract":"<div><div>Sequential recommendation aims to analyze users’ interaction sequences to capture their sustained long-term preferences and dynamically changing short-term preferences for the next item recommendation. Recent studies have shifted their focus to the frequency domain to further mine users’ complex historical interaction behaviors. However, most existing frequency-based methods cannot explicitly distinguish the low-frequency information associated with long-term preferences from the high-frequency information associated with short-term preferences in user sequences. Consequently, they are unable to accurately model these preferences, thereby limiting the performance of the models. To this end, we propose a novel yet simple model based on Dual-Frequency Self-Attention Network (DFSNet) for sequential recommendation. DFSNet comprises low- and high-frequency self-attention modules that separately extract the corresponding components from user sequences to model long- and short-term preferences. Additionally, considering the limited frequency information available within sequences, we introduce contrastive learning to generate self-supervised signals from the preference representations produced by DFSNet. This approach further strengthens the modeling of both long-term and short-term preferences without disrupting the sequence structure, thereby positively impacting the recommendation performance. Extensive experiments on four public datasets indicate that DFSNet outperforms strong baselines while balancing accuracy and efficiency, confirming its effectiveness.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122700"},"PeriodicalIF":6.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119453","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}

{"title":"PUWR-TSSG: A CMAB-based post-unknown worker recruitment scheme for Three-Stage Stackelberg Games in Mobile Crowd Sensing","authors":"Kejia Fan ,&nbsp;Jianheng Tang ,&nbsp;Yaohui Han ,&nbsp;Yuhao Zheng ,&nbsp;Yajiang Huang ,&nbsp;Anfeng Liu ,&nbsp;Neal N. Xiong ,&nbsp;Shaobo Zhang ,&nbsp;Tian Wang ,&nbsp;Mianxiong Dong","doi":"10.1016/j.ins.2025.122693","DOIUrl":"10.1016/j.ins.2025.122693","url":null,"abstract":"<div><div>Numerous Three-Stage Stackelberg Games (TSSG) have been proposed to model the strategic interactions among the requesters, the platform, and the workers in Mobile Crowd Sensing (MCS). However, most existing studies unrealistically assume that the platform possesses prior knowledge of the workers’ credibility either beforehand or after receiving their data. Conversely, in practical scenarios, the credibility of workers remains uncertain even after the submission of their data, which is known as the Post-Unknown Worker Recruitment (PUWR) problem. Given this context, conventional models designed for TSSG cannot be applied to real-world MCS. In this paper, we present the PUWR-TSSG scheme for quality-enhanced worker recruitment in TSSG. Specifically, we avoid the unreasonable assumption in previous works and propose a Double-level Credibility Discovery (DCD) approach with bipartite graph-based matrix completion for accurate credibility verification. Subsequently, based on the DCD approach, we further propose a meticulously designed combinatorial multi-armed bandit mechanism to solve the exploration–exploitation dilemma in untrusted environments. Furthermore, we formulate the payment computation issue as a TSSG, while simultaneously considering the workers’ credibility and verification costs incurred by the PUWR problem. Theoretical analyses validate the existence of Stackelberg Equilibrium in our scheme, ensuring that no participant has an incentive to unilaterally deviate from its optimal strategy. Extensive simulations on a real-world dataset validate the effectiveness of our proposed PUWR-TSSG scheme, significantly enhancing the overall data quality and leading to a remarkable average reduction in regret of up to 85.9% compared to baseline methods.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122693"},"PeriodicalIF":6.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107662","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}

{"title":"Large language model assisted hierarchical reinforcement learning training","authors":"Qianxi Li ,&nbsp;Bao Pang ,&nbsp;Yong Song ,&nbsp;Hongze Fu ,&nbsp;Qingyang Xu ,&nbsp;Xianfeng Yuan ,&nbsp;Xiaolong Xu ,&nbsp;Chengjin Zhang","doi":"10.1016/j.ins.2025.122688","DOIUrl":"10.1016/j.ins.2025.122688","url":null,"abstract":"<div><div>Traditional reinforcement learning (RL) cannot solve complex long-sequence decision tasks, especially when the environment rewards are sparse. Large language models (LLMs) can perform well in long-sequence decision tasks by leveraging their powerful inference capabilities. Although LLMs possess a large amount of general knowledge, LLM-based agents lack expertise in solving specific target problems. Considering that reinforcement learning models are smaller than LLMs and can be trained specifically to perform well on specific tasks, this paper proposes a hierarchical reinforcement learning framework assisted by a large language model, called LLMHRL. In this framework, the LLM acts as a teacher agent to guide the exploration of high-level policy in hierarchical reinforcement learning. The low-level policy consists of a library of selection-based policies. The agent executes specific actions based on the low-level policy chosen by the high-level policy. Furthermore, to reduce the action space of high-level policy, this paper decomposes it into skill options and target options. The two types of options are combined to obtain a high-level policy. This paper evaluates LLMHRL against baseline methods using both public and custom-built harder tasks across three environments: MiniGrid for key-door pairing, ManiSkill for tabletop sorting, and real-world scenarios. The results show that LLMHRL outperforms existing methods in success rate, convergence speed, and average return.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122688"},"PeriodicalIF":6.8,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145119454","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}

{"title":"A relation classification and aggregation algorithm for bipartite-type multi-relational heterogeneous graphs","authors":"Hua Duan,&nbsp;Shiduo Wang,&nbsp;Yufei Zhao,&nbsp;Hua Liu,&nbsp;Xiaotong Li","doi":"10.1016/j.ins.2025.122687","DOIUrl":"10.1016/j.ins.2025.122687","url":null,"abstract":"<div><div>Existing Heterogeneous Graph Neural Networks (HGNNs) are multi-oriented and single-relational heterogeneous graphs, and cannot effectively function on Bipartite-type Multi-relational Heterogeneous Graphs (BMHGs) with multiple relationships. At the same time, existing meta-path-based HGNNs cannot fully consider the differences between meta-paths during the aggregation process, and this difference is even more prominent in BMHGs. The main manifestation is that the number of neighbor nodes connected by various meta-relation paths differs significantly, causing some paths to carry too much noise information, which affects the algorithm performance. In order to solve the problem of the complex relationships in BMHG and the significant disparity in the number of neighbors between paths, this paper proposes a Relation Classification and Aggregation Algorithm for Bipartite-type Multi-Relational Heterogeneous Graphs (RCAA-BMHG). The RCAA-BMHG algorithm consists of three modules: the same-type aggregation module, the across-type aggregation module, and the cross-category feature aggregation layer, which perform differentiated processing of different types of association information between nodes in a Bipartite-type Multi-relational Heterogeneous Graph. Specifically, the same-type aggregation module first introduces a same-type node association filter to distinguish between the densely coupled path and the sparsely coupled path, and then uses a global average strategy and an adaptive weight allocation method to aggregate the information of the two types of coupled paths. The across-type aggregation module is filtered by an across-type node association filter, and then the weighted sum mechanism and the neighborhood feature propagation technology are used to aggregate the information of the two types of coupled paths. Finally, RCAA-BMHG uses a category-level attention mechanism to fuse the semantic and feature information of the same and cross types to generate the final node embedding for downstream tasks. Experimental verification shows that RCAA-BMHG not only performs feature aggregation and classification tasks when processing complex heterogeneous graph data, but also shows significant advantages over existing HGNNs algorithms on multiple evaluation metrics. The complete reproducible code and data have been published at: <span><span>https://github.com/Dylanwsd24/RCAA-BMHG</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122687"},"PeriodicalIF":6.8,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107664","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}

{"title":"Transferable adversarial attacks on human pose estimation: A regularization and pruning framework","authors":"Renguang Chen ,&nbsp;Xuechao Yang ,&nbsp;Xun Yi ,&nbsp;Zhide Chen ,&nbsp;Chen Feng ,&nbsp;Xu Yang ,&nbsp;Kexin Zhu ,&nbsp;Iqbal Gondal","doi":"10.1016/j.ins.2025.122674","DOIUrl":"10.1016/j.ins.2025.122674","url":null,"abstract":"<div><div>Human Pose Estimation (HPE) is a core component in real-time decision systems, supporting critical applications such as healthcare monitoring, autonomous driving, and sports analytics. While deep learning models—particularly CNNs and Transformer-based architectures—have significantly improved HPE accuracy, they remain vulnerable to adversarial perturbations that subtly distort keypoint localization, thereby undermining system reliability. To address this challenge, we propose regularization and pruning transferable adversarial attack (RPA), a novel framework designed to enhance the transferability of adversarial samples in Transformer-based HPE models. RPA integrates two synergistic strategies: gradient regularization, which suppresses dominant feature correlations to reduce overfitting, and adaptive weight pruning, which removes redundant parameters to reduce model-specific noise. This dual mechanism enables the generation of transferable adversarial attacks that are effective across diverse model architectures. Extensive experiments on state-of-the-art HPE networks demonstrate that RPA consistently outperforms existing attack methods. In white-box settings, RPA reduces average precision (AP) by 0.05-0.30; in black-box scenarios, it yields AP drops of 0.01-0.04. These findings expose critical vulnerabilities in IoT-enabled HPE applications and establish a new benchmark for evaluating adversarial robustness in real-time perception systems.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122674"},"PeriodicalIF":6.8,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107118","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}

{"title":"DPRO-GNN: Bridging differential privacy and advanced optimization for privacy-preserving graph learning","authors":"Yanan Bai ,&nbsp;Liji Xiao ,&nbsp;Hongbo Zhao ,&nbsp;Xiaoyu Shi","doi":"10.1016/j.ins.2025.122695","DOIUrl":"10.1016/j.ins.2025.122695","url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) have demonstrated exceptional performance in modeling structured data, yet their application in sensitive domains inevitably raises privacy concerns. Existing Differentially Private GNN (DPGNN) frameworks primarily rely on Differentially Private Stochastic Gradient Descent (DP-SGD) to enforce privacy guarantees. However, DP-SGD inherits its inherent limitations, such as training instability and slow convergence, which are particularly problematic for complex graph learning tasks. Although advanced optimizers like Ranger offer a promising alternative, their naive integration into DPGNN frameworks introduces bias, specifically in the second-moment estimation, due to the additive noise required for DP. To address this challenge, we propose the Differentially Private Ranger-Optimized Graph Neural Network (DPRO-GNN) to protect users’ sensitive data when training the GNN tasks. To mitigate DP noise and capture multi-scale structure, DPRO-GNN applies hierarchical pooling to aggregate nodes into progressively coarser subgraphs, yielding robust, multi-resolution embeddings. Meanwhile, our approach introduces DP-RangerBC, a bias-corrected variant of the Ranger optimizer that mitigates the noise-induced bias in second-order moment estimation, thereby enabling more stable and efficient training under DP constraints. Furthermore, the theoretical analysis of DPRO-GNN, including its correctness and security, is also provided. Extensive experiments on real-world datasets demonstrate that DPRO-GNN achieves superior performance in terms of classification accuracy and convergence speed, compared to state-of-the-art DPGNN methods. The code of DPRO-GNN is available at the following link:<span><span>https://github.com/Silbermondlel/DPRO-GNN</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":51063,"journal":{"name":"Information Sciences","volume":"723 ","pages":"Article 122695"},"PeriodicalIF":6.8,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145107663","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}