检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RTGA: A Redundancy-free Accelerator for High-Performance Temporal Graph Neural Network Inference 24

RTGA: A Redundancy-free Accelerator for High-Performance Tem...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Yu, Hui Zhang, Yu Tan, Andong Lu, Chenze Zhao, Jin Liao, Xiaofei Jin, Hai Liu, Haikun National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9798400706011

Temporal Graph Neural Network (TGNN) has attracted much research attention because it can capture the dynamic nature of complex networks. However, existing solutions suffer from redundant computation overhead and excessive off-chip communications for TGNN inference because they often rely on redundant graph sampling and repeatedly fetching the features and vertex memory. This paper proposes a redundancy-free accelerator, RTGA, for high-performance TGNN inference. Specifically, RTGA proposes a redundancy-aware execution approach with temporal tree into a novel accelerator design to effectively eliminate unnecessary data processing for fewer redundant computations and off-chip communications and also designs a temporal-aware data caching method to improve data locality for TGNN. We have implemented and evaluated RTGA on a Xilinx Alveo U280 FPGA card. Compared with cutting-edge software solutions (i.e., TGN and TGL) and hardware solutions (i.e., BlockGNN and FlowGNN), RTGA improves the performance of TGNN inference by an average of 473.2x, 87.4x, 8.2x, and 6.9x and saves energy by 542.8x, 102.2x, 9.4x, and 8.3x, respectively. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

An API Field Design Method Based on Pre-trained Model 14

An API Field Design Method Based on Pre-trained Model

引用

14th International Conference on Software Technology and engineering, ICSTE 2024

作者： Wang, Hai Lou, Yihua Yang, Yi Xu, Ranbin Yang, Jingbo Liao, Xingchuang Center of Civil Aviation Big Data TravelSky Technology Limited Beijing Engineering Research Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence Beihang University Beijing China

ISBN: (纸本)9798350378955

Application programming interface (API) plays an important role in modern software development, a well designed API can provide tremendous convenience for developers. However, designing an excellent API is not a trivial task, each field in the API should avoid any ambiguity. Besides, in some special cases, for instance, a Chinese developer might not accurately translate the meaning of a Chinese API field into its English counterpart. Therefore, there exists a tremendous requirement in designing high quality API field. In this paper, a fine-tuning pre-trained model based method is proposed for API field design task. Firstly, we consider the design of API fields as a translation task, converting the fields from another language into English. Secondly, we fine-tune a pre-trained model for API field design task. In the end, we curate two datasets to illustrate our method and the experiment results demonstrate that our method has a better performance in designing API field. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Multicomponent Similarity Graphs for Cross-Network Node Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1411-1424页

作者： Zhang, Yuhong Shi, Congmei Li, Xinzheng Zhang, Zan Hu, Xuegang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei230009 China

Cross-network node classification aims to train a classifier for an unlabeled target network using a source network with rich labels. In applications, the degree of nodes mostly conforms to the long-tail distribution, i.e., most nodes in the network are tail nodes with sparse neighborhoods. The established methods focus on either the discrepancy cross network or the long tail in a single network. As for the cross-network node classification under long tail, the coexistence of sparsity of tail nodes and the discrepancy cross-network challenges existing methods for long tail or methods for the cross-network node classification. To this end, a multicomponent similarity graphs for cross-network node classification (MS-CNC) is proposed in this article. Specifically, in order to address the sparsity of the tail nodes, multiple component similarity graphs, including attribute and structure similarity graphs, are constructed for each network to enrich the neighborhoods of the tail nodes and alleviate the long-tail phenomenon. Then, multiple representations are learned from the multiple similarity graphs separately. Based on the multicomponent representations, a two-level adversarial model is designed to address the distribution difference across networks. One level is used to learn the invariant representations cross network in view of structure and attribute components separately, and the other level is used to learn the invariant representations in view of the fused structure and attribute graphs. Extensive experimental results show that the MS-CNC outperforms the state-of-the-art methods. Impact Statement-Node classification is an important task in graph mining. With the unavailability of labels, some researchers propose cross-network node classification, using one labeled network to assist the node classification of another unlabeled network. However, the long-tail of nodes leads to unsatisfactory performance and challenges the recent cross-network node classification m

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

ANIMC: A Soft Approach for Autoweighted Noisy and Incomplete Multiview Clustering

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2022年第2期3卷 192-206页

作者： Fang, Xiang Hu, Yuchong Zhou, Pan Wu, Dapeng Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering The School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Information Storage System Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States

Multiview clustering has wide real-world applications because it can process data from multiple sources. However, these data often contain missing instances and noises, which are ignored by most multiview clustering methods. Missing instances may make these methods difficult to use directly, and noises will lead to unreliable clustering results. In this article, we propose a novel autoweighted noisy and incomplete multiview clustering (ANIMC) approach via a soft autoweighted strategy and a doubly soft regular regression model. First, by designing adaptive semiregularized nonnegative matrix factorization, the soft autoweighted strategy assigns a proper weight to each view and adds a soft boundary to balance the influence of noises and incompleteness. Second, by proposing θ-norm, the doubly soft regularized regression model adjusts the sparsity of our model by choosing different θ. Compared with previous methods, ANIMC has three unique advantages: 1) it is a soft algorithm to adjust our approach in different scenarios, thereby improving its generalization ability;2) it automatically learns a proper weight for each view, thereby reducing the influence of noises;3) it performs doubly soft regularized regression that aligns the same instances in different views, thereby decreasing the impact of missing instances. Extensive experimental results show its superior advantages over other state-of-the-art works. © 2020 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Causal fMRI-Mamba: Causal State Space Model for Neural Decoding and Brain Task States Recognition

Causal fMRI-Mamba: Causal State Space Model for Neural Decod...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Deng, Weihao Han, Fei Ling, Qinghua Liu, Qing Han, Henry School of Computer Science and Communication Engineering JiangSu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China School of Computer Jiangsu University of Science and Technology China School of Electronic and Information Engineering West Anhui University China School of Engineering and Computer Science Baylor University United States

ISBN: (纸本)9798350368741

Deep learning advances neural decoding in functional magnetic resonance imaging (fMRI) tasks with convolution and attention-based methods. However, these methods struggle with capturing global spatiotemporal information due to high dimensionality, noise and inter-individual difference of fMRI, which also increase computational complexity and prior bias. To this end, a novel causal state space model, Causal fMRI-Mamba, is proposed for neural decoding and task state mapping. It effectively captures global spatiotemporal information via eliminating local redundancies and capturing long-distance dependencies. Meanwhile, a causal representation framework is designed to extract invariant high-order features and disentangle related causal features, enhancing model performance. Furthermore, a dense connection module is expanded to prevent significant causal information loss in hidden states of inter layers. On the HCP brain task state classification task, Causal fMRI-Mamba achieves better performance and generalization than comparison methods. © 2025 IEEE.

关键词： causal representation learning Neuro-decoding state space model task-based fMRI

来源：评论

学校读者我要写书评

暂无评论

An end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation

引用

Multimedia Tools and Applications 2025年第16期84卷 16281-16299页

作者： Zhou, Hui Tao, Huanjie Duan, Qianyue Hu, Zhenwu Deng, Yishi School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Cyberspace Security Northwestern Polytechnical University Xi’an710129 China Engineering Research Center of Embedded System Integration Ministry of Education Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China

Weakly supervised pavement crack segmentation aims to assign each pixel of pavement surface images a category label (crack or non-crack) using limited annotation information. Most existing methods adopt the multi-stage approach based on the class activation map (CAM), which outputs from a pre-trained crack classification model, to generate the pixel-level pseudo labels, and then train a segmentation model using these pseudo labels. However, these methods have two notable drawbacks: (i) CAM focuses primarily on the most discriminative regions of the image, potentially resulting in an incomplete estimation of crack regions, and (ii) the process of obtaining pixel-level pseudo labels from CAM is complex and may introduce noise. To avoid these issues, we propose an end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation. Specifically, to better guide the model to pay more attention to the repair process of crack regions, we introduce the segmentation loss, which assigns different weights for crack regions and background regions, through the Residual Project Network. Additionally, to alleviate the impact of the domain gap between synthetic and real datasets, we introduce the consistency loss through the joint training paradigm of unpaired data that incorporates both crack and non-crack images into the training process simultaneously. Furthermore, to enable the model to effectively extract local features and reduce the model's computational complexity, we introduce the Lightweight Multi-head Self-attention module. The experiment results on the CRACK500 dataset, the CFD dataset, and the AEL dataset demonstrate that our model achieves better performance than some existing weakly supervised pavement segmentation methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Towards Stricter Black-box Integrity Verification of Deep Neural Network Models 24

Towards Stricter Black-box Integrity Verification of Deep Ne...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： He, Chaoxiang Bai, Xiaofan Ma, Xiaojing Zhu, Bin B. Hu, Pingyi Fu, Jiayun Jin, Hai Zhang, Dongmei Huazhong University of Science and Technology Hubei Wuhan China Shanghai Jiao Tong University Shanghai China Microsoft Corporation Beijing China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9798400706868

Cloud-based machine learning services offer significant advantages but also introduce the risk of tampering with cloud-deployed deep neural network (DNN) models. Black-box integrity verification (BIV) allows model owners and end-users to determine if a cloud-deployed DNN model has been tampered with by examining only the top-1 label responses. Fingerprinting generates fingerprint samples to query the model, achieving BIV with no impact on the model's accuracy. In this paper, we present BIVBench, the first comprehensive benchmark for BIV of DNN models. BIVBench covers 16 types of model modifications, providing extensive coverage of practical modification scenarios. Our analysis reveals that existing fingerprinting methods, which are typically focused on significant tampering, lack the sensitivity needed to effectively detect subtle yet common and potentially severe modifications. To address this limitation, we propose MiSentry (Model Integrity Sentry), a novel fingerprinting method that leverages meta-learning. MiSentry strategically incorporates a few subtly modified models into the meta-learning model zoo and maximizes the divergence of output predictions between the target model and the modified models in the model zoo to generate highly sensitive, generalizable, and effective fingerprint samples. Extensive evaluations using BIVBench demonstrate that MiSentry outperforms existing state-of-the-art methods overall and significantly surpasses them in detecting subtle modifications. The BIVBench and supplementary materials are available at: https://***/CGCL-codes/BIVBench. © 2024 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Multi-Keyword Fuzzy Adjacency Search Strategy for Encrypted Graph in Cloud Environment

引用

computers, Materials & Continua 2024年第3期78卷 3177-3194页

作者： Bin Wu Xianyi Chen Jinzhou Huang Caicai Zhang Jing Wang Jing Yu Zhiqiang Zhao Zhuolin Mei School of Computer and Big Data Science Jiujiang UniversityJiujiang332005China Jiujiang Key Laboratory of Network and Information Security Jiujiang332005China School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Engineering Hubei University of Arts and ScienceXiangyang441053China School of Modern Information Technology Zhejiang Institute of Mechanical and Electrical EngineeringHangzhou310053China Information Center Jiangxi Changjiang Chemical Co.Ltd.Jiujiang332005China School of Mathematics and Computer Science Ningxia Normal UniversityGuyuan756099China

In a cloud environment,outsourced graph data is widely used in companies,enterprises,medical institutions,and so *** owners and users can save costs and improve efficiency by storing large amounts of graph data on cloud *** on cloud platforms usually have some subjective or objective attacks,which make the outsourced graph data in an insecure *** issue of privacy data protection has become an important obstacle to data sharing and *** to query outsourcing graph data safely and effectively has become the focus of *** query is a basic and frequently used operation in graph,and it will effectively promote the query range and query ability if multi-keyword fuzzy search can be supported at the same *** work proposes to protect the privacy information of outsourcing graph data by encryption,mainly studies the problem of multi-keyword fuzzy adjacency query,and puts forward a *** our scheme,we use the Bloom filter and encryption mechanism to build a secure index and query token,and adjacency queries are implemented through indexes and query tokens on the cloud *** proposed scheme is proved by formal analysis,and the performance and effectiveness of the scheme are illustrated by experimental *** research results of this work will provide solid theoretical and technical support for the further popularization and application of encrypted graph data processing technology.

关键词： Privacy-preserving adjacency query multi-keyword fuzzy search encrypted graph

来源：评论

学校读者我要写书评

暂无评论

CCTG-NET: Contextualized Convolutional Transformer-GRU Network for speech emotion recognition

引用

International Journal of Speech Technology 2023年第4期26卷 1099-1116页

作者： Tellai, Mohammed Mao, Qirong Department of Computer Science and Communication Engineering Jiangsu University Jiangsu Province Zhenjiang212013 China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Jiangsu Province Zhenjiang212013 China

Speech is a crucial aspect of human-to-human interactions and plays a fundamental role in the advancement of human–computer interaction (HCI) systems. Developing an accurate speech emotion recognition (SER) system for human conversations poses a critical yet challenging task. Existing state-of-the-art (SOTA) research in SER primarily focuses on modeling vocal information within individual conversational speech utterances, overlooking the significance of incorporating transactional information from the interaction context. In this paper, we present a novel Contextualized Convolutional Transformer-GRU Network (CCTG-Net) for recognizing speech emotions using Mel-spectrogram features, effectively integrating contextual information for emotion recognition. Our experiments are conducted on the widely-used emotional benchmark dataset, IEMOCAP. Compared to SOTA methods in four-class emotion recognition, our proposed model achieves a weighted accuracy of 88.4% and an unweighted accuracy (UA) of 89.1%. This marks a substantial 3.0% enhancement in UA while maintaining an optimal balance between performance and complexity. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Emotion Recognition

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：