检索结果-内蒙古大学图书馆

Generalized Category Discovery with Large Language Models in the Loop

学校读者我要写书评

暂无评论

arXiv 2023年

作者： An, Wenbin Shi, Wenkai Tian, Feng Lin, Haonan Wang, QianYing Wu, Yaqiang Cai, Mingxiang Wang, Luyan Chen, Yan Zhu, Haiping Chen, Ping School of Automation Science and Engineering Xi’an Jiaotong University China School of Computer Science and Technology Xi’an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering China Lenovo Research China University of Massachusetts Boston United States

Generalized Category Discovery (GCD) is a crucial task that aims to recognize both known and novel categories from a set of unlabeled data by utilizing a few labeled data with only known categories. Due to the lack of supervision and category information, current methods usually perform poorly on novel categories and struggle to reveal semantic meanings of the discovered clusters, which limits their applications in the real world. To mitigate the above issues, we propose Loop, an end-to-end active-learning framework that introduces Large Language Models (LLMs) 1 into the training loop, which can boost model performance and generate category names without relying on any human efforts. Specifically, we first propose Local Inconsistent Sampling (LIS) to select samples that have a higher probability of falling to wrong clusters, based on neighborhood prediction consistency and entropy of cluster assignment probabilities. Then we propose a Scalable Query strategy to allow LLMs to choose true neighbors of the selected samples from multiple candidate samples. Based on the feedback from LLMs, we perform Refined Neighborhood Contrastive Learning (RNCL) to pull samples and their neighbors closer to learn clustering-friendly representations. Finally, we select representative samples from clusters corresponding to novel categories to allow LLMs to generate category names for them. Extensive experiments on three benchmark datasets show that Loop outperforms SOTA models by a large margin and generates accurate category names for the discovered clusters. Code and data are available at https://***/Lackel/LOOP. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

A SUPERVISED INFORMATION ENHANCED MULTI-GRANULARITY CONTRASTIVE LEARNING FRAMEWORK FOR EEG BASED EMOTION RECOGNITION

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Xiang Song, Jian Zhao, Zhigang Wang, Chunxiao Song, Dawei Hu, Bin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Institute of Engineering Medicine Beijing Institute of Technology Beijing China

This study introduces a novel Supervised Info-enhanced Contrastive Learning framework for EEG based Emotion Recognition (SI-CLEER). SI-CLEER employs multi-granularity contrastive learning to create robust EEG contextual representations, potentially improving emotion recognition effectiveness. Unlike existing methods solely guided by classification loss, we propose a joint learning model combining self-supervised contrastive learning loss and supervised classification loss. This model optimizes both loss functions, capturing subtle EEG signal differences specific to emotion detection. Extensive experiments demonstrate SI-CLEER's robustness and superior accuracy on the SEED dataset compared to state-of-the-art methods. Furthermore, we analyze electrode performance, highlighting the significance of central frontal and temporal brain region EEGs in emotion detection. This study offers an universally applicable approach with potential benefits for diverse EEG classification tasks. © 2024, CC0.

关键词： Emotion Recognition

SGD-YOLOv5: A Small Object Detection Model for Complex Industrial Environments

学校读者我要写书评

暂无评论

SGD-YOLOv5: A Small Object Detection Model for Complex Indus...

International Joint Conference on Neural networks (IJCNN)

作者： Jiabin Pei Xiaoming Wu Xiangzhi Liu Longxiang Gao Shui Yu Xi Zheng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science University of Technology Sydney Sydney Australia Macquarie University Sydney Australia

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Due to the complexity of industrial environments, such as construction sites and production workshops, the objects to be detected are easily occluded and perceived as small objects, which poses certain challenges for object detection. To ensure a safe industrial environment, this study adopts YOLOv5 as the basic framework and integrates the depth-to-space convolution module to improve the model’s ability to extract feature information of small targets. Second, the global attention mechanism is incorporated into the network to enhance the global interaction information, reducing the feature information loss, and improving the model performance. Finally, to alleviate the contradiction between classification and regression tasks in object detection, the YOLOv5 head is replaced with a decoupled head to achieve better classification and accelerate model convergence. To improve data diversity and enhance model robustness, we augmented the open-source safety helmet wearing dataset (SHWD) and smoking behavior detection dataset (SBDD). We test the performance of the proposed model (SGD-YOLOv5) on the large and small object detection dataset (SODA-D) and VisDrone2021-DET datasets. Furthermore, its ability to detect small objects was also evaluated. Experiments show that our model outperforms all baseline models on SHWD and SBDD. Compared to the TPH-YOLOv5 on the SODA-D dataset, AP and Recall achieve improvements of 18.3% to 19.2% and 11.9% to 13.3% respectively. On the Visdrone 2021-DET dataset, mAP@0.5 achieved an improvement from 35.45% to 35.70% compared to the state-of-the-art model YOLO-Drone.

关键词： YOLO Head Neural networks Production Feature extraction Robustness Data models

Trusted Auditing of Data Operation Behaviors in Cloud based on Blockchain and TEE

学校读者我要写书评

暂无评论

Trusted Auditing of Data Operation Behaviors in Cloud based ...

IEEE International Conference on Big Data and Cloud computing (BdCloud)

作者： Shujiang Xu Fansheng Wang Lianhai Wang Miodrag J. Mihaljević Shuhui Zhang Wei Shao Qihao Huang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Mathematical Institute the Serbian Academy of Sciences and Arts Belgrade Serbia Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

With the rapid development of the new generation of information technologies, including cloud computing, 5G, and the Internet of Things, data outsourcing storage in the cloud has brought great convenience to data storage or access anytime and anywhere. Due to the separation of ownership and management of outsourced stored data, it faces data security risks, including data loss and personal privacy disclosure. The third-party audit of data operational behavior by logs is often employed to strengthen the security of outsourced data. However, some privacy breach incidents in recent years show that third parties who may leak information about data and users’ identities are not always trustworthy. To achieve data security and privacy protection, an operation behavior auditing scheme for outsourced data is proposed with the blockchain rather than third parties. The data operation behavior audit is carried out from three dimensions: integrity of the operation behavior log, the credibility of the operation behavior information, and compliance of operation behavior. The security analysis and experiment results indicate that this scheme is secure and feasible.

关键词：

Disentangled Representation Learning with Transmitted Information Bottleneck

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dang, Zhuohang Luo, Minnan Jia, Chengyou Dai, Guang Wang, Jihong Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi’an710049 China The SGIT AI Laboratory Xi’an710048 China The State Grid Shaanxi Electric Power Company Ltd. State Grid Corporation of China Xi’an710048 China The School of Information Science and Technology University of Science and Technology of China Hefei230026 China Abu Dhabi United Arab Emirates Baidu Inc Beijing100085 China

Encoding only the task-related information from the raw data, i.e., disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop;2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose DisTIB (Transmitted Information Bottleneck for Disentangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses. Copyright © 2023, The Authors. All rights reserved.

关键词： Information theory

Adaptive Fine-grained Access Control Method in Social Internet of Things

学校读者我要写书评

暂无评论

International Journal of network security 2021年第1期23卷 42-48页

作者： Zhang, Hongbin Ma, Pengcheng Liu, Bin School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang China Hebei Key Laboratory of Network and Information Security Hebei Normal China School of Economics and Management Hebei University of Science China Technology Research Center of Big Data and Social Computing Hebei University of Science China

Social Internet of Things (SloT), as a new carrier of integration of social and Internet of Things, applies the research results of social networks from different aspects of the Internet of Things. Different types of connected intelligent objects interact socially, compared with random data access between them, access control technology is more stringent. This paper integrates social attributes into attributebased access control of Internet of Things, initializes relational attribute tags, and labels social interest attributes for different objects, then quantifes tag similarity and implements initial access control authorization, integrates social attributes into game theory to dynamically adjust access control policies, so the adaptive finegrained division of access control under the Social Internet of Things is effectively realized. The experimental results show that our method can not only effectively carry out initial authorization according to tag similarity, but also further adaptively adjust the permission policy according to social attributes, and further meet the finegrained partition requirements of access control, which is ensure the effective implementation of access control under the Social Internet of things. © 2021. All Rights Reserved.

关键词： Game theory

From Data Integrity to Global ModeI Integrity for Decentralized Federated Learning: A Blockchain-based Approach

学校读者我要写书评

暂无评论

From Data Integrity to Global ModeI Integrity for Decentrali...

International Joint Conference on Neural networks (IJCNN)

作者： Na Wang Yao Zhao Youyang Qu Lei Cui Bai Li Longxiang Gao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of IT Deakin University VIC Australia Zhejiang Tianheng Information Technology Company China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Decentralized Federated Learning (DFL) is extensively applied in various areas, e.g., healthcare, finance, and Internet of Things (loT), offering practical solutions for distributed intelligent applications and data collaboration. In DFL systems, participants, e.g., edge devices, organizations, or nodes, collaborate in the training of a shared global model by aggregating local models from various participants. During this process, participants need to communicate frequently with a central authority/node/server to share model parameters. Such communication is vulnerable to malicious attacks or tampering, posing a significant threat to the integrity of model training. The integrity verification method can provide an integrity guarantee for the global model of DFL. However, most of the existing integrity verification schemes are centralized and not suitable for resource-constrained DFL scenarios. Therefore, how to verify the integrity of the global model becomes an important issue in DFL. To address it, we devise a global model integrity verification method for DFL. Specifically, we generate a digital signature for each global model parameter as proof of integrity, while improving the efficiency of integrity verification by electing delegates to conduct the verification process. A series of experiments is conducted to validate the performance of the proposed method. The experimental results demonstrate that our approach not only effectively ensures the integrity of the global model but also functions well under limited resources.

关键词： Training Federated learning Data integrity Neural networks Finance Distributed databases Organizations

Grouped Federated Meta-Learning for Privacy-Preserving Rare Disease Diagnosis

学校读者我要写书评

暂无评论

Grouped Federated Meta-Learning for Privacy-Preserving Rare ...

International Joint Conference on Neural networks (IJCNN)

作者： Xinru Song Feng Wu Zongchao Xie Longxiang Gao Lei Cui Youyang Qu Shujun Gu Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Computer Science University of Technology Sydney Australia Faculty of Science University of Melbourne Australia

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Federated learning (FL) has been widely applied in medical field, which allows clients to collaboratively train global models without sharing local data. Nevertheless, the diversity and scarcity of samples from rare diseases may result in a decline in the performance of local models on client-side due to using a singular global model. Moreover, direct transmission of local models or parameters will likely lead to user privacy violations. To solve these problems, we propose a Grouped Federated Meta-Learning (GrFML) method to improve the performance of local personalization models while protecting data privacy. Specifically, we first utilize a self-attention mechanism to extract partial features from the client’s local data, which are uploaded to the server (medical data is susceptible to perturbation and data integrity, thus this process does not expose the private data). The server groups clients with similar features based on these extracted features. Then, multiple meta-models are trained on these groups and distributed back to the clients to enhance the performance of the client’s local models. Furthermore, during the FL process, we introduce dynamic perturbation to the uploaded gradients based on the model’s test accuracy to protect their privacy. Typically, the perturbation magnitude is directly proportional to the model’s test accuracy. Extensive experiments shown that the GrFML model significantly improves client personalization model accuracy and achieves a good privacy-utility trade-off.

关键词： Metalearning Privacy Data privacy Accuracy Perturbation methods Feature extraction Data models

Frequency synchronization for uplink massive MIMO systems

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zhang, Weile Gao, Feifei Jin, Shi Lin, Hai MOE Key Lab for Intelligent Networks and Network Security Xi'An Jiaotong University Xi'an Shaanxi710049 China State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Automation Tsinghua University Beijing100084 China National Communications Research Laboratory Southeast University Nanjing210096 China Department of Electrical and Information Systems Osaka Prefecture University Osaka Japan

In this paper, we propose a frequency synchronization scheme for multiuser orthogonal frequency division multiplexing (OFDM) uplink with a large-scale uniform linear array (ULA) at base station (BS) by exploiting the angle information of users. Considering that the incident signal at BS from each user can be restricted within a certain angular spread, the proposed scheme could perform carrier frequency offset (CFO) estimation for each user individually through a joint spatial-frequency alignment procedure and can be completed efficiently with the aided of fast Fourier transform (FFT). A multi-branch receive beamforming is further designed to yield an equivalent single user transmission model for which the conventional singleuser channel estimation and data detection can be carried out. To make the study complete, the theoretical performance analysis of the CFO estimation is also conducted. We further develop a user grouping scheme to deal with the unexpected scenarios that some users may not be separated well from the spatial domain. Finally, various numerical results are provided to verify the proposed studies. Copyright © 2017, The Authors. All rights reserved.

关键词： Orthogonal frequency division multiplexing