检索结果-内蒙古大学图书馆

Coarse-to-fine lightweight meta-embedding for ID-based recommendations

science China(information sciences) 2025年第4期68卷 82-97页

作者： Yang WANG Haipeng LIU Zeqian YI Biao QIAN Meng WANG School of Computer Science and Information Engineering Hefei University of Technology College of Information and Intelligence Hunan Agricultural University

State-of-the-art recommender systems are increasingly focused on optimizing implementation efficiency, such as enabling on-device recommendations under memory constraints. Current methods commonly use lightweight embeddings for users and items or employ compact embeddings to enhance reusability and reduce memory usage. However, these approaches consider only the coarse-grained aspects of embeddings, overlooking subtle semantic nuances. This limitation results in an adversarial degradation of meta-embedding performance, impeding the system's ability to capture intricate relationships between users and items, leading to suboptimal recommendations. To address this, we propose a novel approach to efficiently learn meta-embeddings with varying grained and apply fine-grained meta-embeddings to strengthen the representation of their coarse-grained counterparts. Specifically, we introduce a recommender system based on a graph neural network, where each user and item is represented as a node. These nodes are directly connected to coarse-grained virtual nodes and indirectly linked to fine-grained virtual nodes, facilitating learning of multi-grained semantics. Fine-grained semantics are captured through sparse meta-embeddings, which dynamically balance embedding uniqueness and memory constraints. To ensure their sparseness, we rely on initialization methods such as sparse principal component analysis combined with a soft thresholding activation function. Moreover, we propose a weight-bridging update strategy that aligns coarse-grained meta-embedding with several fine-grained meta-embeddings based on the underlying semantic properties of users and items. Comprehensive experiments demonstrate that our method outperforms existing baselines. The code of our proposal is available at https://***/htyjers/C2F-MetaEmbed.

关键词： lightweight meta-embedding coarse-to-fine learning ID-based recommendations

来源：评论

学校读者我要写书评

暂无评论

Malicious iOS Apps Detection Through Multi-Criteria Decision-Making Approach

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第1期49卷 207-220页

作者： Bhatt, Arpita Jadhav Sardana, Neetu Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Indonesia

In today’s era, smartphones are used in daily lives because they are ubiquitous and can be customized by installing third-party apps. As a result, the menaces because of these apps, which are potentially risky for user’s privacy, have increased. information on smartphones is perhaps, more personal than compared to data stored on desktops or computers, making it an easy target for intruders. After Android, the most prevalently used mobile operating system is Apple’s iOS. Both Android and iOS follow permission-based access control to protect user’s privacy. However, the users are unaware whether the app is breaching the user’s privacy. To combat this problem, in the paper we propose a hybrid approach to detect malicious iOS apps based on its permissions. In the first phase, weights have been assigned to app permissions using multi-criteria decision-making (MCDM) approach namely Analytic Hierarchy Process (AHP), and in the second phase machine learning& ensemble learning techniques have been employed to train the classifiers for detecting malicious apps. To test the efficacy of the proposed method dataset comprising 1150 apps from 12 app categories has been used. The results demonstrate the proposed approach improves the efficacy of detecting malicious iOS apps for majority of categories. © 2025 Slovene Society Informatika. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Enhanced Acceleration for Generalized Nonconvex Low-Rank Matrix Learning

引用

Chinese Journal of Electronics 2025年第1期34卷 98-113页

作者： Hengmin Zhang Jian Yang Wenli Du Bob Zhang Zhiyuan Zha Bihan Wen School of Electrical and Electronic Engineering Nanyang Technological University School of Computer Science and Engineering Nanjing University of Science and Technology School of Information Science and Engineering East China University of Science and Technology Department of Electrical and Computer Engineering University of Macau

Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.

关键词： Learning systems Image recognition Minimization Computational efficiency Complexity theory Matrix decomposition Optimization Image reconstruction Singular value decomposition Convergence

来源：评论

学校读者我要写书评

暂无评论

Robust video question answering via contrastive cross-modality representation learning

引用

science China(information sciences) 2024年第10期67卷 211-226页

作者： Xun YANG Jianming ZENG Dan GUO Shanshan WANG Jianfeng DONG Meng WANG School of Information Science and Technology University of Science and Technology of China Institute of Artificial Intelligence Hefei Comprehensive National Science Center School of Computer Science and Information Engineering Hefei University of Technology Institutes of Physical Science and Information Technology Anhui University School of Computer Science and Technology Zhejiang Gongshang University

Video question answering(VideoQA) is a challenging yet important task that requires a joint understanding of low-level video content and high-level textual semantics. Despite the promising progress of existing efforts, recent studies revealed that current VideoQA models mostly tend to over-rely on the superficial correlations rooted in the dataset bias while overlooking the key video content, thus leading to unreliable results. Effectively understanding and modeling the temporal and semantic characteristics of a given video for robust VideoQA is crucial but, to our knowledge, has not been well investigated. To fill the research gap, we propose a robust VideoQA framework that can effectively model the cross-modality fusion and enforce the model to focus on the temporal and global content of videos when making a QA decision instead of exploiting the shortcuts in datasets. Specifically, we design a self-supervised contrastive learning objective to contrast the positive and negative pairs of multimodal input, where the fused representation of the original multimodal input is enforced to be closer to that of the intervened input based on video perturbation. We expect the fused representation to focus more on the global context of videos rather than some static keyframes. Moreover, we introduce an effective temporal order regularization to enforce the inherent sequential structure of videos for video representation. We also design a Kullback-Leibler divergence-based perturbation invariance regularization of the predicted answer distribution to improve the robustness of the model against temporal content perturbation of videos. Our method is model-agnostic and can be easily compatible with various VideoQA backbones. Extensive experimental results and analyses on several public datasets show the advantage of our method over the state-of-the-art methods in terms of both accuracy and robustness.

关键词： video question answering cross-modality fusion contrastive learning cross-media reasoning

来源：评论

学校读者我要写书评

暂无评论

Exploration of alzheimer disease using design of experiments

引用

Multimedia Tools and Applications 2025年第3期84卷 1079-1101页

作者： Gupta, Pranav Pandey, Kavita Gupta, Sanskar Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India

This study examines the use of experimental designs, specifically full and fractional factorial designs, for predicting Alzheimer’s disease with fewer variables. The full factorial design systematically investigates the effects of selected factors, providing a comprehensive analysis of their individual and interactive impacts on Alzheimer’s prediction. On the other hand, the fractional factorial design simplifies the model by selecting key factors and removing non-significant ones. For Alzheimer’s, among all the factors examined, the MMSE (Mini-mental state Examination) score emerged as the most significant, which was further cross-validated using Minitab Software Analysis. Importantly, the findings suggest that the fractional factorial design is a better alternative, particularly when time and cost constraints are present. The results highlight the effectiveness and efficiency of these experimental designs, demonstrating their potential for early detection, prevention, and treatment of Alzheimer’s disease. By contributing to the expanding knowledge base on experimental designs in medical research, this study emphasizes their crucial role in understanding and combating complex diseases like Alzheimer’s. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Design of experiments

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

science China(information sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

A Weakly-Supervised Crowd Density Estimation Method Based on Two-Stage Linear Feature Calibration

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 965-981页

作者： Yong-Chao Li Rui-Sheng Jia Ying-Xiang Hu Hong-Mei Sun the College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590 the Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266000China the College of Computer Science and Engineering Shandong University of Science and TechnologyQingdao 266590China the College of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210000China

In a crowd density estimation dataset,the annotation of crowd locations is an extremely laborious task,and they are not taken into the evaluation *** this paper,we aim to reduce the annotation cost of crowd datasets,and propose a crowd density estimation method based on weakly-supervised learning,in the absence of crowd position supervision information,which directly reduces the number of crowds by using the number of pedestrians in the image as the supervised *** this purpose,we design a new training method,which exploits the correlation between global and local image features by incremental learning to train the ***,we design a parent-child network(PC-Net)focusing on the global and local image respectively,and propose a linear feature calibration structure to train the PC-Net simultaneously,and the child network learns feature transfer factors and feature bias weights,and uses the transfer factors and bias weights to linearly feature calibrate the features extracted from the Parent network,to improve the convergence of the network by using local features hidden in the crowd *** addition,we use the pyramid vision transformer as the backbone of the PC-Net to extract crowd features at different levels,and design a global-local feature loss function(L2).We combine it with a crowd counting loss(LC)to enhance the sensitivity of the network to crowd features during the training process,which effectively improves the accuracy of crowd density *** experimental results show that the PC-Net significantly reduces the gap between fullysupervised and weakly-supervised crowd density estimation,and outperforms the comparison methods on five datasets of Shanghai Tech Part A,ShanghaiTech Part B,UCF_CC_50,UCF_QNRF and JHU-CROWD++.

关键词： Crowd density estimation linear feature calibration vision transformer weakly-supervision learning

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Deep Learning Techniques for the Detection of Grape Diseases

引用

Recent Advances in computer science and Communications 2024年第2期17卷 1-12页

作者： Pandey, Kavita Chandak, Abhimanyu Department of Computer Science & Engineering and Information Technology Jaypee Institute of Information Technology Noida India

Plant diseases are one of the major contributors to economic loss in the agriculture industry worldwide. Detection of disease at early stages can help in the reduction of this loss. In recent times, a lot of emphasis has been done on disease detection due to the overall increase in production as well as the loss of grape number. With deep learning, having a promising future and having the advantages of automatic learning and feature extraction, the use of these techniques has now been widely spread. This paper reviewed the existing deep-learning techniques available for grape disease detection. Firstly, covering the various steps in a grape disease detection model ranging from the various sources of image acquisition, the different image augmentation techniques and the various models used, and the parameters required to evaluate. Secondly, the study summarizes the im-portant findings of all literature available on the theme. The paper also tries to highlight the various challenges faced by the researchers and the common trend among them, so that future research on the topic can achieve higher performance. © 2024, Bentham science Publishers. All rights reserved.

关键词： Losses

来源：评论

学校读者我要写书评

暂无评论

Global-local term fusion for optimised community Q&A topic modelling

引用

International Journal of Innovative Computing and Applications 2024年第1期15卷 50-69页

作者： Prabha, Sneh Sardana, Neetu Department of Computer Science and Engineering and Information Technology Jaypee Institute of Information Technology Noida India

Community question and answer (Q&A) websites have become invaluable information and knowledge-sharing sources. Effective topic modelling on these platforms is crucial for organising and navigating the vast amount of user-generated content. To address these challenges, we propose a novel global-local term fusion with optimised community (GLOCOM) Q&A topic modelling approach that leverages both local and global term importance to enhance topic modelling on community Q&A websites. GLOCOM combines term frequency-inverse document frequency for local importance and entropy for global importance. Further, we employ fuzzy clustering to enhance the representation of multifaceted topics. Furthermore, clustering results are optimised using a genetic algorithm (GA) to refine cluster assignments and centroids. We compared the proposed model with baseline models LDA and FLSA. GLOCOM has performed consistently well for all topic numbers. It has shown an improvement of 8.86% in silhouette score as compared to LDA and excelled for datasets with size > 3 MB. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

ESG Investing: A Statistically Valid Approach to Data-Driven Decision Making and the Impact of ESG Factors on Stock Returns and Risk

引用

IEEE Access 2024年 12卷 69434-69444页

作者： Teja, Kamurthi Ravi Liu, Chuan-Ming National Taipei University of Technology International Program of Electrical Engineering and Computer Science Taipei10608 Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei10608 Taiwan

This study examines the impact of environmental, social, and governance (ESG) factors on economic investment from a statistical perspective, aiming to develop a tested investment strategy that capitalizes on the connection between ESG factors and financial performance. ESG investing: A statistically valid approach to data-driven decision-making (ESGI-SVADDM) investment strategy is based on a rigorous, statistically valid approach that utilizes data, math, statistics, and data science libraries to drive investment decisions, eliminating the need for personal opinions and subjectivity. The process includes establishing an investment thesis, formulating testable hypotheses (HPS), retrieving and refining relevant data, calculating relevant measures, and testing and validating all hypotheses. The study uses S&P 500 stock data and ESG data from Sustainalytics to test the hypotheses. The empirical tests conducted revealed a negative correlation between ESG risk and expected returns, as well as a positive trend in the relationship between ESG risk and the overall risk of stocks. Moreover, the study found that higher ESG risk scores are associated with lower returns for investors, and that adopting a strategy of investing in stocks with low ESG risk and shorting stocks with high ESG risk yields superior returns compared to the market portfolio. © 2013 IEEE.

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：