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

Enhance the Performance of Directional Feature-based Palmprint Recognition by Directional Response Stability Measurement

引用

Machine Intelligence Research 2024年第3期21卷 597-614页

作者： Haitao Wang Wei Jia School of Computer Science and Information Engineering Hefei University of TechnologyHefei230009China

Palmprint recognition is an emerging biometrics technology that has attracted increasing attention in recent years. Many palmprint recognition methods have been proposed, including traditional methods and deep learning-based methods. Among the traditional methods, the methods based on directional features are mainstream because they have high recognition rates and are robust to illumination changes and small noises. However, to date, in these methods, the stability of the palmprint directional response has not been deeply studied. In this paper, we analyse the problem of directional response instability in palmprint recognition methods based on directional feature. We then propose a novel palmprint directional response stability measurement (DRSM) to judge the stability of the directional feature of each pixel. After filtering the palmprint image with the filter bank, we design DRSM according to the relationship between the maximum response value and other response values for each pixel. Using DRSM, we can judge those pixels with unstable directional response and use a specially designed encoding mode related to a specific method. We insert the DRSM mechanism into seven classical methods based on directional feature, and conduct many experiments on six public palmprint databases. The experimental results show that the DRSM mechanism can effectively improve the performance of these methods. In the field of palmprint recognition, this work is the first in-depth study on the stability of the palmprint directional response, so this paper has strong reference value for research on palmprint recognition methods based on directional features.

关键词： Biometrics palmprint recognition directional response stability directional coding-based methods directional feature

来源：评论

学校读者我要写书评

暂无评论

Biometrics 2.0 for the Security of Smart Cities

引用

Machine Intelligence Research 2024年第6期21卷 1121-1144页

作者： Wei Jia Zhecheng Zhang Yang Zhao Hai Min Shujie Li School of Computer Science and Information Engineering Hefei University of TechnologyHefei230009China

In modern society,an increasing number of occasions need to effectively verify people's *** is the most ef-fective technology for personal *** research on automated biometrics recognition mainly started in the 1960s and *** the following 50 years,the research and application of biometrics have achieved fruitful *** 2014-2015,with the successful applications of some emerging information technologies and tools,such as deep learning,cloud computing,big data,mobile communication,smartphones,location-based services,blockchain,new sensing technology,the Internet of Things and federated learning,biometric technology entered a new development ***,taking 2014-2015 as the time boundary,the development of biometric technology can be divided into two *** addition,according to our knowledge and understanding of biometrics,we fur-ther divide the development of biometric technology into three phases,i.e.,biometrics 1.0,2.0 and *** 1.0 is the primary de-velopment phase,or the traditional development *** 2.0 is an explosive development phase due to the breakthroughs caused by some emerging information *** present,we are in the development phase of biometrics *** 3.0 is the future development phase of *** the biometrics 3.0 phase,biometric technology will be fully mature and can meet the needs of various *** 1.0 is the initial phase of the development of biometric technology,while biometrics 2.0 is the advanced *** this paper,we provide a brief review of biometrics ***,the concept of biometrics 2.0 is defined,and the architecture of biometrics 2.0 is *** particular,the application architecture of biometrics 2.0 in smart cities is *** challenges and perspectives of biometrics 2.0 are also discussed.

关键词： Biometrics smart city security application architecture

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

Privacy-preserving recommendation with coarse-grained spatiotemporal contexts

引用

science China(information sciences) 2025年第4期68卷 66-81页

作者： Lei CHEN Chen GAO Jiahuan LEI Xiaoyi DU Xinlei SHI Hengliang LUO Depeng JIN Yong LI Meng WANG Department of Electronic Engineering BNRist Tsinghua University Meituan Inc. School of Computer Science and Information Engineering Hefei University of Technology

The behavior of users on online life service platforms like Meituan and Yelp often occurs within specific finegrained spatiotemporal contexts(i.e., when and where). Recommender systems, designed to serve millions of users, typically operate in a fully server-based manner, requiring on-device users to upload their behavioral data, including fine-grained spatiotemporal contexts, to the server, which has sparked public concern regarding privacy. Consequently, user devices only upload coarse-grained spatiotemporal contexts for user privacy protection. However, previous research mostly focuses on modeling fine-grained spatiotemporal contexts using knowledge graph convolutional models, which are not applicable to coarse-grained spatiotemporal contexts in privacy-constrained recommender systems. In this paper, we investigate privacy-preserving recommendation by leveraging coarse-grained spatiotemporal contexts. We propose the coarse-grained spatiotemporal knowledge graph for privacy-preserving recommendation(CSKG), which explicitly models spatiotemporal co-occurrences using common-sense knowledge from coarse-grained contexts. Specifically, we begin by constructing a spatiotemporal knowledge graph tailored to coarse-grained spatiotemporal contexts. Then we employ a learnable metagraph network that integrates common-sense information to filter and extract co-occurrences. CSKG evaluates the impact of coarsegrained spatiotemporal contexts on user behavior through the use of a knowledge graph convolutional network. Finally, we introduce joint learning to effectively learn representations. By conducting experiments on two real large-scale datasets,we achieve an average improvement of about 11.0% on two ranking metrics. The results clearly demonstrate that CSKG outperforms state-of-the-art baselines.

关键词： privacy-preserveing coarse-grained spatiotemporal contexts recommender systems

来源：评论

学校读者我要写书评

暂无评论

Inductive Lottery Ticket Learning for Graph Neural Networks

引用

Journal of computer science & technology 2024年第6期39卷 1223-1237页

作者： Yong-Duo Sui Xiang Wang Tianlong Chen Meng Wang Xiang-Nan He Tat-Seng Chua School of Data Science University of Science and Technology of ChinaHefei 230027China Department of Electrical and Computer Engineering The University of Texas at AustinAustin 78712U.S.A School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China School of Computing National University of SingaporeSingapore

Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.

关键词： lottery ticket hypothesis graph neural networks neural network pruning

来源：评论

学校读者我要写书评

暂无评论

Representation learning: serial-autoencoder for personalized recommendation

引用

Frontiers of computer science 2024年第4期18卷 61-72页

作者： Yi ZHU Yishuai GENG Yun LI Jipeng QIANG Xindong WU School of Information Engineering Yangzhou UniversityYangzhou 225127China Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education of the People’s Republic of China) Hefei University of TechnologyHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China

Nowadays,the personalized recommendation has become a research hotspot for addressing information *** this,generating effective recommendations from sparse data remains a ***,auxiliary information has been widely used to address data sparsity,but most models using auxiliary information are linear and have limited *** to the advantages of feature extraction and no-label requirements,autoencoder-based methods have become quite ***,most existing autoencoder-based methods discard the reconstruction of auxiliary information,which poses huge challenges for better representation learning and model *** address these problems,we propose Serial-Autoencoder for Personalized Recommendation(SAPR),which aims to reduce the loss of critical information and enhance the learning of feature ***,we first combine the original rating matrix and item attribute features and feed them into the first autoencoder for generating a higher-level representation of the ***,we use a second autoencoder to enhance the reconstruction of the data representation of the prediciton rating *** output rating information is used for recommendation *** experiments on the MovieTweetings and MovieLens datasets have verified the effectiveness of SAPR compared to state-of-the-art models.

关键词： personalized recommendation autoencoder representation learning collaborative filtering

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

Mitigation of Optical Multipath Interference Algorithms in IM-DD Transmission System

引用

China Communications 2024年第4期21卷 1-9页

作者： Huo Jiahao Zhu Jin Zhu Zuqing Zhang Xiaoying Liu Shaonan Tao Jianlong Wei Huangfu School of Computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Information Science and Technology University of Science and Technology of ChinaHefei 230026China

This paper aimed to propose two algorithms,DA-M and RF-M,of reducing the impact of multipath interference(MPI)on intensity modulation direct detection(IM-DD)systems,particularly for four-level pulse amplitude modulation(PAM4)***-M reduced the fluctuation by averaging the signal in blocks,RF-M estimated MPI by subtracting the decision value of the corresponding block from the mean value of a signal block,and then generated interference-reduced samples by subtracting the interference signal from the product of the corresponding MPI estimate and then weighting *** paper firstly proposed to separate the signal before decision-making into multiple blocks,which significantly reduced the complexity of DA-M and *** results showed that the MPI noise of 28 GBaud IMDD system under the linewidths of 1e5 Hz,1e6 Hz and 10e6 Hz can be effectively alleviated.

关键词： IM-DD multipath interference PAM4

来源：评论

学校读者我要写书评

暂无评论

Bootstrap-Based Layerwise Refining for Causal Structure Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2708-2722页

作者： Xiang, Guodu Wang, Hao Yu, Kui Guo, Xianjie Cao, Fuyuan Song, Yukun Hefei University of Technology Key Laboratory of Knowledge Engineering with the Big Data of Ministry of Education Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China Shanxi University School of Computer and Information Technology Taiyuan030006 China

Learning causal structures from observational data is critical for causal discovery and many machine learning tasks. Traditional constraint-based methods first adopt conditional independence (CI) tests to learn a global skeleton layer by layer and then orient the undirected edges to obtain a causal structure. However, the reliability of these statistical tests largely depends on the quality of data samples. In real-life scenarios, the presence of data noise or limited samples often makes many CI tests unreliable at each layer in the skeleton learning phase, leading to an inaccurate skeleton. As the number of layers increases, the inaccurate skeleton will continue to impair the skeleton construction of subsequent layers. Furthermore, an unreliable skeleton hampers the skeleton orientation procedure, resulting in an unsatisfactory causal structure. In this article, we propose a Bootstrap-based layerwise refining (BLR) algorithm for causal structure learning, which includes two new procedures to solve the above problems. First, BLR utilizes a novel layerwise skeleton refining procedure to construct the global skeleton layer by layer based on the bootstrap sampling. Second, BLR employs a collective skeleton orientation procedure that incorporates scoring techniques to collectively orient the global skeleton. The experimental results show that BLR outperforms the state-of-the-art methods on the benchmark Bayesian Network datasets. © 2020 IEEE.

关键词： Refining

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：