检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Huang, Junjie Cao, Qi Xie, Ruobing Zhang, Shaoliang Xia, Feng Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China WeChat Tencent Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Recently, Graph Neural Networks (GNNs) achieve remarkable success in Recommendation. To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance. Most GCL methods consist of data augmentation and contrastive loss (e.g., InfoNCE). GCL methods construct the contrastive pairs by hand-crafted graph augmentations and maximize the agreement between different views of the same node compared to that of other nodes, which is known as the InfoMax principle. However, improper data augmentation will hinder the performance of GCL. InfoMin principle, that the good set of views shares minimal information and gives guidelines to design better data augmentation. In this paper, we first propose a new data augmentation (i.e., edge-operating including edge-adding and edge-dropping). Then, guided by InfoMin principle, we propose a novel theoretical guiding contrastive learning framework, named Learnable data Augmentation for Graph Contrastive Learning (LDA-GCL). Our methods include data augmentation learning and graph contrastive learning, which follow the InfoMin and InfoMax principles, respectively. In implementation, our methods optimize the adversarial loss function to learn data augmentation and effective representations of users and items. Extensive experiments on four public benchmark datasets demonstrate the effectiveness of LDA-GCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

The Domination Game: Dilating Bubbles to Fill Up Pareto Fronts

The Domination Game: Dilating Bubbles to Fill Up Pareto Fron...

引用

2023 IEEE Congress on Evolutionary Computation, CEC 2023

作者： Coelho, Vasco Papetti, Daniele M. Tangherloni, Andrea Cazzaniga, Paolo Besozzi, Daniela Nobile, Marco S. University of Milano-Bicocca Department of Informatics Systems and Communication Milan Italy Bocconi Institute for Data Science and Analytics Bocconi University Department of Computing Sciences Milan Italy University of Bergamo Department of Human and Social Sciences Bergamo Italy Ca' Foscari University of Venice Department of Environmental Sciences Informatics and Statistics Venice Italy

ISBN: (纸本)9798350314588

Multi-objective optimization algorithms might struggle in finding optimal dominating solutions, especially in real-case scenarios where problems are generally characterized by non-separability, non-differentiability, and multi-modality issues. An effective strategy that already showed to improve the outcome of optimization algorithms consists in manipulating the search space, in order to explore its most promising areas. In this work, starting from a Pareto front identified by an optimization strategy, we exploit Local Bubble Dilation Functions (LBDFs) to manipulate a locally bounded region of the search space containing non-dominated solutions. We tested our approach on the benchmark functions included in the DTLZ and WFG suites, showing that the Pareto front obtained after the application of LBDFs is most of the time characterized by an increased hyper-volume value. Our results confirm that LBDFs are an effective means to identify additional non-dominated solutions that can improve the quality of the Pareto front. © 2023 IEEE.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Federated Learning with Differential Privacy Via Fast Fourier Transform for Tighter-Efficient Combining

SSRN

引用

SSRN 2023年

作者： Guo, Shengnan Yang, Jianfeng Long, Shigong Wang, Xibin Liu, Guangyuan State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China School of Big Data Laboratory of Electrical Power Big Data of Guizhou Province Guizhou Institute of Technology Guiyang55005 China

Spurred by the simultaneous need for data privacy protection and data sharing, federated learning has been proposed. However, there is still a risk of privacy leakage in it. In this paper, an improved differential privacy algorithm is proposed to protect the federated learning model. And at the same time, the Fast Fourier Transform is used in the computation of the privacy budget , to minimize the impact of limited arithmetic resources and numerous users on the effectiveness of the training model. Then, discarding the various discussions that were directly on the privacy budget instead, FFT is used together with PLD in this process for calculating consumption, which further tightens the bound of computation with minimal impact on the efficiency. Moreover, the activation function for model training is improved by using a temper sigmoid with only one parameter , which much smoother the accuracy curve and reduces the drastic fluctuating scenarios. Finally, simulation results on real datasets show that the federated learning with the DP algorithm that considers the long trailing case facilitates better equalizing the relationship between privacy and utility. © 2023, The Authors. All rights reserved.

关键词： Fast Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

Learnable Broad Learning for Semi-Supervised Specific Emitter Identification in the Internet of Everything

Learnable Broad Learning for Semi-Supervised Specific Emitte...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Zhang, Yibin Peng, Yang Wang, Qin Lin, Yun Gui, Guan Niyato, Dusit Adachi, Fumiyuki College of Telecommunications and Information Engineering Njupt Nanjing China College of Information and Communication Engineering Harbin Engineering University Harbin China College of Computing and Data Science Nanyang Technological University Singapore International Research Institute of Disaster Science Tohoku University Sendai Japan

ISBN: (纸本)9798350368369

Specific emitter identification (SEI) is crucial in the Internet of Everything (IoE). Over the past decade, deep learning (DL) and broad learning (BL)-enabled SEI technologies have emerged. Recently, many researchers have begun exploring semi-supervised learning techniques to address the semi-supervised SEI (SS-SEI) problem with limited labeled RF signals. However, existing SS-SEI solutions often prioritize identification performance, leading to high computational overheads and lacking iterability. To overcome these challenges, this paper proposes a novel SS-SEI solution based on a learnable broad learning network (LBL). Initially, a pretrained DL-based SEI model is downloaded to the edge device. Meanwhile, an updatable BL-based SEI method is deployed locally on the edge device to identify unlabelled signals. When the LBL solution is operational, edge devices capture real-time unlabelled RF signals. The pretrained DL-based SEI method and the locally BL-based SEI method jointly identify these RF signals. The identification results and the new real-time RF signals are then used to update the weights of the BL-based SEI method at the edge devices. The LBL SS-SEI solution is validated using an open-source, large-scale, real-world automatic dependent surveillance-broadcast (ADS-B) dataset. Experimental results demonstrate that the proposed LBL solution offers significant advantages regarding SS-SEI performance. © 2025 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

ALOFT: A Lightweight MLP-Like Architecture with Dynamic Low-Frequency Transform for Domain Generalization

ALOFT: A Lightweight MLP-Like Architecture with Dynamic Low-...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jintao Guo Na Wang Lei Qi Yinghuan Shi State Key Laboratory for Novel Software Technology Nanjing University National Institute of Healthcare Data Science Nanjing University School of Computer Science and Engineering Southeast University

Domain generalization (DG) aims to learn a model that generalizes well to unseen target domains utilizing multiple source domains without re-training. Most existing DG works are based on convolutional neural networks (CNNs). However, the local operation of the convolution kernel makes the model focus too much on local representations (e.g., texture), which inherently causes the model more prone to overfit to the source domains and hampers its generalization ability. Recently, several MLP-based methods have achieved promising results in supervised learning tasks by learning global interactions among different patches of the image. Inspired by this, in this paper, we first analyze the difference between CNN and MLP methods in DG and find that MLP methods exhibit a better generalization ability because they can better capture the global representations (e.g., structure) than CNN methods. Then, based on a recent lightweight MLP method, we obtain a strong baseline that outperforms most state-of-the-art CNN-based methods. The baseline can learn global structure representations with a filter to suppress structureirrelevant information in the frequency space. Moreover, we propose a dynAmic LOw-Frequency spectrum Transform (ALOFT) that can perturb local texture features while preserving global structure features, thus enabling the filter to remove structure-irrelevant information sufficiently. Extensive experiments on four benchmarks have demonstrated that our method can achieve great performance improvement with a small number of parameters compared to SOTA CNN-based DG methods. Our code is available at https://***/lingeringlight/ALOFT/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta-Transfer Learning Based Cross-Domain Gesture Recognition Using WiFi Channel State Information

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Dai, Penglin Zhou, Junfei Ma, Jialong Zhang, Hao Wu, Xiao Southwest Jiaotong University School of Computing and Artificial Intelligence Chengdu611756 China Ministry of Education Engineering Research Center of Sustainable Urban Intelligent Transportation China Tangshan Institute of Southwest Jiaotong University Tangshan063000 China Chongqing University of Posts and Telecommunications College of Computer Science and Technology Key Laboratory of Data Engineering and Visual Computing Chongqing400065 China

Gesture recognition plays a crucial role in a wide range of consumer electronics applications, including human-computer interaction and virtual reality, by enabling the identification and interpretation of human gestures. In recent times, WiFi-based gesture recognition has garnered significant attention due to its privacy protection and unobtrusive nature. However, this approach heavily depends on neural network-based models and is notably influenced by environmental conditions, such as specific location and orientation. To address these environmental impacts, we propose a network framework that leverages transfer learning and meta-learning. The primary focus is on utilizing transfer learning to train a convolutional neural network (ResNet) for feature extraction, enabling the extraction of domain-independent features specifically related to gestures, rather than being influenced by environmental factors. Additionally, we employ the meta-learning algorithm MAML to train the fully connected network for gesture classification. Following training, a small set of samples can be utilized for rapid adaptation to diverse domains, maintaining high accuracy across different domains to achieve cross-domain gesture recognition. Our performance evaluation is based on the Widar 3.0 dataset, encompassing both in-domain and cross-domain scenarios. The simulation results demonstrate that our proposed algorithm surpasses Widar3.0 and WiGRUNT by approximately 7.9% and 1.12% in gesture recognition accuracy across all scenarios. © 2025 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction

arXiv

引用

arXiv 2023年

作者： Luo, Haoran Haihong, E. Yang, Yuhao Yao, Tianyu Guo, Yikai Tang, Zichen Zhang, Wentai Peng, Shiyao Wan, Kaiyang Song, Meina Lin, Wei Zhu, Yifan Tuan, Luu Anh School of Computer Science Beijing University of Posts and Telecommunications China School of Automation Science and Electrical Engineering Beihang University China Beijing Institute of Computer Technology and Application China Inspur Group Co. Ltd. China College of Computing and Data Science Nanyang Technological University Singapore

Beyond traditional binary relational facts, n-ary relational knowledge graphs (NKGs) are comprised of n-ary relational facts containing more than two entities, which are closer to real-world facts with broader applications. However, the construction of NKGs remains at a coarse-grained level, which is always in a single schema, ignoring the order and variable arity of entities. To address these restrictions, we propose Text2NKG, a novel fine-grained n-ary relation extraction framework for n-ary relational knowledge graph construction. We introduce a span-tuple classification approach with hetero-ordered merging and output merging to accomplish fine-grained n-ary relation extraction in different arity. Furthermore, Text2NKG supports four typical NKG schemas: hyper-relational schema, event-based schema, role-based schema, and hypergraph-based schema, with high flexibility and practicality. The experimental results demonstrate that Text2NKG achieves state-of-the-art performance in F1 scores on the fine-grained n-ary relation extraction benchmark. Our code and datasets are publicly available1 © 2023, CC BY-NC-SA.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

3D Skull Completion via Two-stage Conditional Diffusion-Based Signed Distance Fields

3D Skull Completion via Two-stage Conditional Diffusion-Base...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Liu, Zhenhong Ru, Xudong Wang, Xingce Wu, Zhongke Zhu, Yi-Cheng Zhang, Chong Frangi, Alejandro F. Beijing Normal University School of Artificial Intelligence Beijing China Peking Union Medical College Hospital Department of Neurology Beijing China Bioimage Analysis Barcelona Spain School of Engineering University of Manchester Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences Department of Computer Science United Kingdom Department of Cardiovascular Sciences Department of Electrical Engineering Leuven Belgium Alan Turing Institute London United Kingdom

ISBN: (纸本)9798350386226

A fast and fully automatic design of 3D cranial implants is highly desired in cranioplasty, and is key to the treatment of skull trauma. We have defined the repair of skull defects as a 3D shape completion task by proposing a two-stage diffusion model based on the representation of 3D shapes using signed distance function (SDF). Specifically, we design a diffusion model conditioned on partial shapes, we compress the 3D shape into a compact latent representation using the encoder in the vector quantized variational autoencoder (VQ-VAE) and learn the diffusion model based on this compressed discrete representation. Encoding the latent space with the autoencoder can achieve high-quality 3D cranial shape completion. In order to accurately capture local and fine-grained shape details, the training data is geometrically encoded from a compactly learned code-book. The two-stage diffusion generator with a coarse-to-fine approach possesses precise and expressive structural modeling capabilities to ensure the supplementation of detailed geometric information. Experimental results verified sufficient expressiveness of our model with generating high-fidelity results with fine-grained local details, outperforming the state-of-the-art methods. © 2024 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

The association among dairy consumption and bone biomarkers in Japanese adults: Cross sectional data analysis from the Iwaki health promotion project

引用

Clinical Nutrition ESPEN 2024年 63卷 1231-1232页

作者： Nakano, A. Ueno, H.M. Kawata, D. Tatara, Y. Tamada, Y. Mikami, T. Murashita, K. Nakaji, S. Itoh, K. Department of Precision Nutrition for Dairy Foods Hirosaki University Graduate School of Medicine Hirosaki Milk Science Research Institute Megmilk Snow Brand Co. Ltd. Kawagoe Department of Medical Data Intelligence Research Center for Health-Medical Data Science Department of Preemptive Medicine Innovation Center for Health Promotion Research Institute of Health Innovation Department of Social Medicine Hirosaki University Graduate School of Medicine Department of Stress Response Science Biomedical Research Center Hirosaki University Graduate School of Medicine Hirosaki Japan

来源：评论

学校读者我要写书评

暂无评论

DomainAdaptor: A Novel Approach to Test-time Adaptation

DomainAdaptor: A Novel Approach to Test-time Adaptation

引用

International Conference on Computer Vision (ICCV)

作者： Jian Zhang Lei Qi Yinghuan Shi Yang Gao State Key Laboratory for Novel Software Technology Nanjing University National Institute of Healthcare Data Science Nanjing University School of Computer Science and Engineering Southeast University

To deal with the domain shift between training and test samples, current methods have primarily focused on learning generalizable features during training and ignore the specificity of unseen samples that are also critical during the test. In this paper, we investigate a more challenging task that aims to adapt a trained CNN model to unseen domains during the test. To maximumly mine the information in the test data, we propose a unified method called DomainAdaptor for the test-time adaptation, which consists of an AdaMixBN module and a Generalized Entropy Minimization (GEM) loss. Specifically, AdaMixBN addresses the domain shift by adaptively fusing training and test statistics in the normalization layer via a dynamic mixture co-efficient and a statistic transformation operation. To further enhance the adaptation ability of AdaMixBN, we design a GEM loss that extends the Entropy Minimization loss to better exploit the information in the test data. Extensive experiments show that DomainAdaptor consistently outperforms the state-of-the-art methods on four benchmarks. Furthermore, our method brings more remarkable improvement against existing methods on the few-data unseen domain. The code is available at https://***/koncle/DomainAdaptor.

关键词：

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：