检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural information Processing Systems

作者： Chengzhi Lin Ancong Wu Junwei Liang Jun Zhang Wenhang Ge Wei-Shi Zheng Chunhua Shen School of Computer Science and Engineering Sun Yat-sen University China AI Thrust Hong Kong University of Science and Technology (Guangzhou) Tencent Youtu Lab School of Computer Science and Engineering Sun Yat-sen University China and Guangdong Province Key Laboratory of Information Security PR China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Zhejiang University

ISBN: (纸本)9781713871088

Cross-modal retrieval between videos and texts has gained increasing research interest due to the rapid emergence of videos on the web. Generally, a video contains rich instance and event information and the query text only describes a part of the information. Thus, a video can correspond to multiple different text descriptions and queries. We call this phenomenon the "Video-Text Correspondence Ambiguity" problem. Current techniques mostly concentrate on mining local or multi-level alignment between contents of a video and text (e.g., object to entity and action to verb). It is difficult for these methods to alleviate the video-text correspondence ambiguity by describing a video using only one single feature, which is required to be matched with multiple different text features at the same time. To address this problem, we propose a Text-Adaptive Multiple Visual Prototype Matching model, which automatically captures multiple prototypes to describe a video by adaptive aggregation of video token features. Given a query text, the similarity is determined by the most similar prototype to find correspondence in the video, which is termed text-adaptive matching. To learn diverse prototypes for representing the rich information in videos, we propose a variance loss to encourage different prototypes to attend to different contents of the video. Our method outperforms the state-of-the-art methods on four public video retrieval datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A mutual authentication lightweight rfid protocol for iot devices 2nd

A mutual authentication lightweight rfid protocol for iot de...

引用

2nd International Cognitive Cities Conference, IC3 2019

作者： Lu, Yong Wang, Anxi Liu, Shuai School of Management Science and Engineering Nanjing University of Information Science and Technology Nanjing210044 China Guizhou Provincial Key Laboratory of Public Big Data GuiZhou University GuiyangGuizhou550025 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou510632 China

ISBN: (纸本)9789811561122

The IoT data security is a hot topic at a data time. Personal privacy data may be easily leaked to data collectors in an open network environment. If the collectors get enough data, they can analyze the habit and interest of every IoT user, which may give helpful advice or cause endless harass. RFID authentication protocol in IoT is a powerful way to avoid the essential data leaked to data collectors. The previous protocols protect the security of RFID system. But they cannot guard the privacy of RFID system. The protocol we proposed achieves both the privacy and security. © Springer Nature Singapore Pte Ltd 2020.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Social Bot Detection via Structural information Theory

arXiv

引用

arXiv 2024年

作者： Peng, Hao Zhang, Jingyun Huang, Xiang Hao, Zhifeng Li, Angsheng Yu, Zhengtao Yu, Philip S. School of Cyber Science and Technology Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China State Key Laboratory of Public Big Data Guizhou University No. 2708 South Section of Huaxi Avenue Huaxi District Guizhou Province Guiyang City550025 China Guangxi Key Lab of Multi-source Information Mining & Security Guangxi Normal University Guilin541004 China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China College of Science University of Shantou No. 243 University Road Shantou515063 China School of Computer Science and Engineering Beihang University No. 37 Xue Yuan Road Haidian District Beijing100191 China Faculty of Information Engineering and Automation Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology Kunming650500 China Department of Computer Science University of Illinois at Chicago ChicagoIL60607 United States

Research on social bot detection plays a crucial role in maintaining the order and reliability of information dissemination while increasing trust in social interactions. The current mainstream social bot detection models rely on black-box neural network technology, e.g., Graph Neural Network, Transformer, etc., which lacks interpretability. In this work, we present UnDBot, a novel unsupervised, interpretable, yet effective and practical framework for detecting social bots. This framework is built upon structural information theory. We begin by designing three social relationship metrics that capture various aspects of social bot behaviors: Posting Type Distribution, Posting Influence, and Follow-to-follower Ratio. Three new relationships are utilized to construct a new, unified, and weighted social multi-relational graph, aiming to model the relevance of social user behaviors and discover long-distance correlations between users. Second, we introduce a novel method for optimizing heterogeneous structural entropy. This method involves the personalized aggregation of edge information from the social multi-relational graph to generate a two-dimensional encoding tree. The heterogeneous structural entropy facilitates decoding of the substantial structure of the social bots network and enables hierarchical clustering of social bots. Thirdly, a new community lab.ling method is presented to distinguish social bot communities by computing the user's stationary distribution, measuring user contributions to network structure, and counting the intensity of user aggregation within the community. Compared with ten representative social bot detection approaches, comprehensive experiments demonstrate the advantages of effectiveness and interpretability of UnDBot on four real social network datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： information theory

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognition

arXiv

引用

arXiv 2022年

作者： Xie, Kan Zhang, Zhe Li, Bo Kang, Jiawen Niyato, Dusit Xie, Shengli Wu, Yi The School of Automation Guangdong University of Technology Guangzhou510006 China The Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China The Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou510006 China The Guangdong Key Laboratory of IoT Information Technology Guangzhou510006 China The School of Data Science and Technology Heilongjiang University Harbin150080 China The Institute for Cryptology & Network Security Heilongjiang University Harbin150080 China School of Computer Science and Engineering Nanyang Technological University Singapore

With the gradual popularization of self-driving, it is becoming increasingly important for vehicles to smartly make the right driving decisions and autonomously obey traffic rules by correctly recognizing traffic signs. However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information. To address this issue, we first exploit privacy-preserving federated learning to perform collab.rative training for accurate recognition models without sharing raw traffic sign data. Nevertheless, due to the limited computing and energy resources of most devices, it is hard for vehicles to continuously undertake complex artificial intelligence tasks. Therefore, we introduce powerful Spike Neural Networks (SNNs) into traffic sign recognition for energy-efficient and fast model training, which is the next generation of neural networks and is practical and well-fitted to IoV scenarios. Furthermore, we design a novel encoding scheme for SNNs based on neuron receptive fields to extract information from the pixel and spatial dimensions of traffic signs to achieve high-accuracy training. Numerical results indicate that the proposed federated SNN outperforms traditional federated convolutional neural networks in terms of accuracy, noise immunity, and energy efficiency as well. Copyright © 2022, The Authors. All rights reserved.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Aided Network Architecture Generation for JPEG Image Steganalysis 20

Reinforcement Learning Aided Network Architecture Generation...

引用

8th ACM Workshop on information Hiding and Multimedia security, IH and MMSec 2020

作者： Yang, Jianhua Lu, Beiling Xiao, Liang Kang, Xiangui Shi, Yun-Qing Guangdong Key Lab of Information Security Sun Yat-Sen University Guangzhou Guangdong China Department of Communication Engineering Xiamen University Xiamen Fujian China School of Data and Computer Science Sun Yat-Sen University Guangzhou Guangdong China Department of ECE New Jersey Institute of Technology NewarkNJ United States

ISBN: (纸本)9781450370509

The architectures of convolutional neural networks used in steganalysis have been designed heuristically. In this paper, an automatic Network Architecture Generation algorithm based on reinforcement learning for JPEG image Steganalysis (JS-NAG) has been proposed. Different from the automatic neural network generation methods in computer vision which are based on the strong content signals, steganalysis is based on the weak embedded signals, thus needs specific design. In the proposed method, the agent is trained to sequentially select some high-performing blocks using Q-learning to generate networks. An early stop strategy and a well-designed performance prediction function have been utilized to reduce the search time. To generate the optimal networks, hundreds of networks have been searched and trained on 3 GPUs for 15 days. To further improve the detection accuracy, we make an ensemble classifier out of the generated convolutional neural networks. The experimental results have shown that the proposed method significantly outperforms the current state-of-the-art CNN based methods. © 2020 ACM.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

data-Efficient Federated Semi-Supervised Learning Framework Via Pseudo Supervision Refinement Strategy for Lung Tumor Segmentation

SSRN

引用

SSRN 2024年

作者： Shi, Zhenwei Li, Weixing Pan, Xipeng Zhang, Zhen Wu, Guangyao Ye, Guanchao Wee, Leonard Dekker, Andre Han, Chu Shi, Lei Liu, Zaiyi Liu, Zhenbing School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Department of Radiology Huazhong University of Science and Technology Tongji Medical College Union Hospital Hubei Wuhan430021 China Clinical Data Science Faculty of Health Medicine Life Sciences Maastricht University Maastricht6229 ET Netherlands GROW School of Oncology and Reproduction Maastricht University Medical Centre+ Maastricht6229 ET Netherlands Guangdong Provincial People's Hospital China

Background and Objective: Accurate lung tumor segmentation is crucial for early clinical diagnosis and subsequent treatment planning for patients. Conducting centralized training to enhance model performance is impractical in real-world scenarios. Although federated learning offers a promising solution to this issue, effectively and efficiently utilizing unlab.led data remains a challenge. Methods: In this work, we propose a novel federated semi-supervised learning framework (FSSL) for complex and realistic scenario, which can efficiently leverage the limited lab.led data and abundant unlab.led data from multiple clinical sites. Specifically, we initially conduct federated self-supervised pre-training at completely unlab.led sites using masked image modeling strategy. Subsequently, in the fine-tuning stage, we propose a pseudo supervision refinement strategy to leverage the unlab.led data from partially lab.led sites, which not only reduces pseudo lab.l noise but also helps stabilize the training process. Moreover, we propose a dynamic model aggregation strategy to assist the server in dynamically combining all local models during communication round. Results: We conducted extensive comparative and ablation experiments to validate the effectiveness of our proposed method. When only a limited amount of lab.led data is availab.e in the partially lab.led sites, even without loading the pre-trained model, our approach consistently achieves the highest average Dice scores of 0.7383, 0.4768, and 0.6629 on the internal test sets, external unseen test sets, and pre-training test sets, respectively. Upon loading the pre-trained model, the scores on the three test sets further improve to 0.8205, 0.6185, and 0.7334, respectively. Conclusion: Our proposed method is capable of collab.ratively training a global model with robust segmentation performance and generalizability by efficiently utilizing unlab.led data from different sites, even when only a limited amount of lab.led da

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

data-Efficient Federated Semi-Supervised Learning Framework Via Pseudo Supervision Refinement Strategy for Lung Tumor Segmentation

SSRN

引用

SSRN 2024年

作者： Shi, Zhenwei Li, Weixing Pan, Xipeng Zhang, Zhen Wu, Guangyao Ye, Guanchao Wee, Leonard Andre, Dekker Han, Chu Shi, Lei Liu, Zaiyi Liu, Zhenbing School of Computer and Information Security Guilin University of Electronic Technology Guilin541004 China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Chinese Academy of Sciences Zhejiang Hangzhou310022 China Department of Radiology Huazhong University of Science and Technology Tongji Medical College Union Hospital Hubei Wuhan430021 China Clinical Data Science Faculty of Health Medicine Life Sciences Maastricht University Maastricht6229 ET Netherlands GROW School of Oncology and Reproduction Maastricht University Medical Centre+ Maastricht6229 ET Netherlands Guangdong Provincial People's Hospital China

Accurate lung tumor segmentation is crucial for early clinical diagnosis and subsequent treatment planning for patients. Centralized model training faces privacy constraints, although federated learning offers a promising solution to this issue, effectively and efficiently utilizing unlab.led data remains a challenge. In this work, we propose a novel federated semi-supervised learning framework for complex and realistic scenario, which can efficiently leverage the limited lab.led data and more homogeneous unlab.led data from multiple clinical sites for collab.rative model training. Specifically, we initially conduct federated self-supervised pre-training at completely unlab.led sites using masked image modeling strategy. Subsequently, in the fine-tuning stage, we propose a pseudo supervision refinement strategy to leverage the unlab.led data from partially lab.led sites, which not only reduces pseudo lab.l noise but also helps stabilize the training process. Moreover, we propose a dynamic model aggregation strategy to assist the server in dynamically combining local models during each communication round to enhance the robustness and generalizability of the global model. Extensive comparative and ablation experiments confirm the efficacy of our proposed methodology, demonstrating improvement over recent state-of-the-art federated semi-supervised segmentation methods in scenarios with only a small amount of lab.led data. This approach highlights the significant potential of multi-source and heterogeneous unlab.led data in facilitating the training of federated deep learning models and promotes clinical applications, assists radiologists in diagnosis and improves patient outcomes. The source code will be released on https://***/zhenweishi/FedPSR © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

G3SR: Global Graph Guided Session-based Recommendation

arXiv

引用

arXiv 2022年

作者： Deng, Zhi-Hong Wang, Chang-Dong Huang, Ling Lai, Jian-Huang Yu, Philip S. School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China College of Mathematics and Informatics South China Agricultural University Guangzhou China Guangdong Provincial Key Laboratory of Public Finance and Taxation with Big Data Application China University of Illinois at Chicago ChicagoIL United States

Session-based recommendation tries to make use of anonymous session data to deliver high-quality recommendation under the condition that user-profiles and the complete historical behavioral data of a target user are unavailab.e. Previous works consider each session individually and try to capture user interests within a session. Despite their encouraging results, these models can only perceive intra-session items and cannot draw upon the massive historical relational information. To solve this problem, we propose a novel method named G3SR (Global Graph Guided Session-based Recommendation). G3SR decomposes the session-based recommendation workflow into two steps. First, a global graph is built upon all session data, from which the global item representations are learned in an unsupervised manner. Then, these representations are refined on session graphs under the graph networks, and a readout function is used to generate session representations for each session. Extensive experiments on two real-world benchmark datasets show remarkable and consistent improvements of the G3SR method over the state-of-the-art methods, especially for cold items. Copyright © 2022, 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

iGniter: Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud

arXiv

引用

arXiv 2022年

作者： Xu, Fei Xu, Jianian Chen, Jiabin Chen, Li Shang, Ruitao Zhou, Zhi Liu, Fangming The Shanghai Key Laboratory of Multidimensional Information Processing School of Computer Science and Technology East China Normal University 3663 N. Zhongshan Road Shanghai200062 China The School of Computing and Informatics University of Louisiana at Lafayette 301 East Lewis Street LafayetteLA70504 United States The Guangdong Key Laboratory of Big Data Analysis and Processing School of Computer Science and Engineering Sun Yat-sen University 132 E. Waihuan Road Guangzhou510006 China The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China

GPUs are essential to accelerating the latency-sensitive deep neural network (DNN) inference workloads in cloud datacenters. To fully utilize GPU resources, spatial sharing of GPUs among co-located DNN inference workloads becomes increasingly compelling. However, GPU sharing inevitably brings severe performance interference among co-located inference workloads, as motivated by an empirical measurement study of DNN inference on EC2 GPU instances. While existing works on guaranteeing inference performance service level objectives (SLOs) focus on either temporal sharing of GPUs or reactive GPU resource scaling and inference migration techniques, how to proactively mitigate such severe performance interference has received comparatively little attention. In this paper, we propose iGniter, an interference-aware GPU resource provisioning framework for cost-efficiently achieving predictable DNN inference in the cloud. iGniter is comprised of two key components: (1) a lightweight DNN inference performance model, which leverages the system and workload metrics that are practically accessible to capture the performance interference;(2) A cost-efficient GPU resource provisioning strategy that jointly optimizes the GPU resource allocation and adaptive batching based on our inference performance model, with the aim of achieving predictable performance of DNN inference workloads. We implement a prototype of iGniter based on the NVIDIA Triton inference server hosted on EC2 GPU instances. Extensive prototype experiments on four representative DNN models and datasets demonstrate that iGniter can guarantee the performance SLOs of DNN inference workloads with practically acceptable runtime overhead, while saving the monetary cost by up to 25% in comparison to the state-of-the-art GPU resource provisioning strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Doubly-Recursive Block Markov Superposition Transmission: A Low-Complexity and Flexible Coding Scheme

Doubly-Recursive Block Markov Superposition Transmission: A ...

引用

作者： Zhao, Shancheng Ma, Xiao Huang, Qin Bai, Baoming College of Information Science and Technology Jinan University Guangzhou510632 China Guangdong Key Laboratory of Data Security and Privacy Preserving Guangzhou510632 China School of Data and Computer Science Sun Yat-sen University Guangzhou510275 China School of Electronic and Information Engineering Beihang University Beijing100083 China State Key Laboratory of ISN Xidian University Xi'an710071 China

In this paper, we introduce a novel method, called doubly-recursive block Markov superposition transmission (DrBMST), to construct high-performance spatially coupled codes. An important characteristic of DrBMST codes is that the degrees of the constraint nodes in their normal graphs are at most three. As a result, DrBMST codes can be decoded with low complexity. We first prove that the error probability of an enlarged DrBMST code ensemble can be made arbitrarily small under windowed maximum-likelihood decoding (MLD) by increasing the decoding window size. This result partially explains the superior performances of DrBMST codes. Then we propose to use the extrinsic information transfer (EXIT) chart analysis to estimate the iterative windowed decoding thresholds of DrBMST codes. The EXIT chart analyses show that, with such a simple structure, DrBMST codes are comparable to BMST codes with large encoding memories in terms of decoding thresholds. Finally, we carry out comparisons to validate the advantages of DrBMST codes in terms of error performances and decoding complexities. In particular, for a decoding latency of 20,000 bits, the DrBMST code performs better than the (4, 8)-regular spatially coupled low-density parity-check (SC-LDPC) code, but with lower computational complexity. Hence, DrBMST codes can be used in communication systems with limited computational resources. In addition, we show that DrBMST can be used to construct multiple-rate codes. © 2020 IEEE.

关键词： Convolutional codes

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：