检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhang, Jin Liu, Ze Lian, Defu Chen, Enhong School of Artificial Intelligence and Data Science University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China

Two-stage recommender systems play a crucial role in efficiently identifying relevant items and personalizing recommendations from a vast array of options. This paper, based on an error decomposition framework, analyzes the generalization error for two-stage recommender systems with a tree structure, which consist of an efficient tree-based retriever and a more precise yet time-consuming ranker. We use the Rademacher complexity to establish the generalization upper bound for various tree-based retrievers using beam search, as well as for different ranker models under a shifted training distribution. Both theoretical insights and practical experiments on real-world datasets indicate that increasing the branches in tree-based retrievers and harmonizing distributions across stages can enhance the generalization performance of two-stage recommender systems. © 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

Few-shot Temporal Pruning Accelerates Diffusion Models for Text Generation 30

Few-shot Temporal Pruning Accelerates Diffusion Models for T...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Li, Bocheng Gao, Zhujin Zhu, Yongxin Yin, Kun Cao, Haoyu Jiang, Deqiang Xu, Linli School of Computer Science and Technology University of Science and Technology of China China School of Data Science University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent YouTu Lab China

ISBN: (纸本)9782493814104

Diffusion models have achieved significant success in computer vision and shown immense potential in natural language processing applications, particularly for text generation tasks. However, generating high-quality text using these models often necessitates thousands of iterations, leading to slow sampling rates. Existing acceleration methods either neglect the importance of the distribution of sampling steps, resulting in compromised performance with smaller number of iterations, or require additional training, introducing considerable computational overheads. In this paper, we present Few-shot Temporal Pruning, a novel technique designed to accelerate diffusion models for text generation without supplementary training while effectively leveraging limited data. Employing a Bayesian optimization approach, our method effectively eliminates redundant sampling steps during the sampling process, thereby enhancing the generation speed. A comprehensive evaluation of discrete and continuous diffusion models across various tasks, including machine translation, question generation, and paraphrasing, reveals that our approach achieves competitive performance even with minimal sampling steps after down to less than 1 minute of optimization, yielding a significant acceleration of up to 400x in text generation tasks. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

SMAKAP: Secure Mutual Authentication and Key Agreement Protocol for RFID Systems 17

SMAKAP: Secure Mutual Authentication and Key Agreement Proto...

引用

17th International Conference on Security of Information and Networks, SIN 2024

作者： Naziri, Shayesta Wang, Xu Yu, Guangsheng Xu, Jian Shrestha, Sudhir Liang, Christy Jie School of Electrical and Data Engineering University of Technology SydneyNSW2007 Australia School of Computer Science University of Technology SydneyNSW2007 Australia

ISBN: (纸本)9798331509736

Radio Frequency Identification (RFID) is a crucial technology in the Internet of Things (IoT), enabling seamless wireless communication and data exchange. However, these technologies can pose significant security chal-lenges if not implemented with proper attention to security protocols-especially in communication, where pre-shared keys are not used between active tags and readers for device authentication. Some recent authentication protocols rely solely on a hash function, nonce, and single public kay agreement, which can lead to failure to implement robust security and proper authentication or ineffective for high security application environments. To effectively address these challenges this paper proposes a secure Elliptic Curve Cryptography (ECC) based lightweight mutual authentication protocol utilizing a hybrid key agreement protocol between active tag and reader for secure communication in RFID-enabled devices in the IoT environments. The informal analysis demonstrates a secure communication environment for data privacy and flexibility through effective key management. This protocol is adaptable to various applications by addressing specific requirements and limitations. © 2024 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

A survey on graph neural network-based next POI recommendation for smart cities

引用

Journal of Reliable Intelligent Environments 2024年第3期10卷 299-318页

作者： Yu, Jian Guo, Lucas Zhang, Jiayu Wang, Guiling Department of Computer Science and Soft Engineering Auckland University of Technology Auckland New Zealand School of Information Science and Technology Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data North China University of Technology Beijing China

Amid the rise of mobile technologies and Location-Based Social Networks (LBSNs), there’s an escalating demand for personalized Point-of-Interest (POI) recommendations. Especially pivotal in smart cities, these systems aim to enhance user experiences by offering location recommendations tailored to past check-ins and visited POIs. Distinguishing itself from traditional POI recommendations, the next POI approach emphasizes predicting the immediate subsequent location, factoring in both geographical attributes and temporal patterns. This approach, while promising, faces with challenges like capturing evolving user preferences and navigating data biases. The introduction of Graph Neural Networks (GNNs) brings forth a transformative solution, particularly in their ability to capture high-order dependencies between POIs, understanding deeper relationships and patterns beyond immediate connections. This survey presents a comprehensive exploration of GNN-based next POI recommendation approaches, delving into their unique characteristics, inherent challenges, and potential avenues for future research. © The Author(s) 2024.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

PRESS: Defending Privacy in Retrieval-Augmented Generation via Embedding Space Shifting

PRESS: Defending Privacy in Retrieval-Augmented Generation v...

引用

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

作者： He, Jiaming Liu, Cheng Hou, Guanyu Jiang, Wenbo Li, Jiachen School of Computer Science and Engineering University of Electronic Science and Technology of China China College of Computer Science and Cyber Security Oxford Brookes College Chengdu University of Technology China School of Data Science The Chinese University of Hong Kong Shenzhen China School of Computer Science and Artificial Intelligence Wuhan University of Technology China

ISBN: (纸本)9798350368741

Retrieval-augmented generation (RAG) expands the capabilities of large language models (LLMs) in various applications by integrating relevant information retrieved from external data sources. However, the RAG systems are exposed to substantial privacy risks during the information retrieval process, leading to potential data leakage of private information. In this work, we present a Privacy-preserving Retrieval-augmented generation via Embedding Space Shifting (PRESS), systematically exploring how to protect privacy in RAG systems. Specifically, we first conduct proximal policy optimization (PPO) based training on pre-trained language models to generate target training samples. Then we employ a purposive shift fine-tuning on the text embedding model with the generated samples for guiding the RAG system to map potential privacy leaking queries to safe target in embedding space. Extensive experimental results on representative models and datasets demonstrate that our protection method achieves high defense performance with high efficiency while keeping the normal functionality of the RAG system. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ILRM: Imitation Learning-Based Resource Management for Integrated CPU–GPU Edge Systems With Renewable Energy Sources

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第6期44卷 2392-2397页

作者： Hou, Xiangpeng Zhou, Junlong Li, Liying Zhao, Mingzhou Cong, Peijin Wu, Zebin Hu, Shiyan Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Southeast University National Mobile Communications Research Laboratory Nanjing211111 China University of Hong Kong Department of Data and Systems Engineering Hong Kong Hong Kong

This letter focuses on integrated CPU-GPU edge systems with renewable energy sources and studies the resource management problem to minimize the energy consumption of real-time tasks while ensuring temperature and reliability constraints. We propose an imitation learning (IL)-based resource management scheme, ILRM, implemented in two phases: 1) offline Oracle generation and 2) online IL. In the offline phase, we design a fast-converging heuristic to generate near-optimal solutions (i.e., Oracles) for training an online prediction model. In the online phase, we realize IL using the trained model that predicts the resource configuration policies for the incoming task sets to be scheduled. A data aggregation method is also developed to enhance the robustness of the prediction model. We validate ILRM through extensive experiments on both simulated and real integrated CPU-GPU edge platforms. © 1982-2012 IEEE.

关键词： Graphics processing units Reliability Central Processing Unit Renewable energy sources Real-time systems Integrated circuit modeling Imitation learning Generators Energy consumption Edge computing

来源：评论

学校读者我要写书评

暂无评论

Enhancing Adversarial Example Transferability via Regularized Constrained Feature Layer

引用

computers, Materials & Continua 2025年第4期83卷 157-175页

作者： Xiaoyin Yi Long Chen Jiacheng Huang Ning Yu Qian Huang School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing400065China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing401420China School of Cyber Security and Information Law Chongqing University of Posts and TelecommunicationsChongqing400065China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of EducationChongqing400065China Artificial Intelligence and Big Data College Chongqing Polytechnic University of Electronic TechnologyChongqing401331China

Transfer-based Adversarial Attacks(TAAs)can deceive a victim model even without prior *** is achieved by leveraging the property of adversarial *** is,when generated from a surrogate model,they retain their features if applied to other models due to their good ***,adversarial examples often exhibit overfitting,as they are tailored to exploit the particular architecture and feature representation of source ***,when attempting black-box transfer attacks on different target models,their effectiveness is *** solve this problem,this study proposes an approach based on a Regularized Constrained Feature Layer(RCFL).The proposed method first uses regularization constraints to attenuate the initial examples of low-frequency *** are then added to a pre-specified layer of the source model using the back-propagation technique,in order to modify the original adversarial ***,a regularized loss function is used to enhance the black-box transferability between different target *** proposed method is finally tested on the ImageNet,CIFAR-100,and Stanford Car datasets with various target models,The obtained results demonstrate that it achieves a significantly higher transfer-based adversarial attack success rate compared with baseline techniques.

关键词： Adversarial examples black-box transferability regularized constrained transfer-based adversarial attacks

来源：评论

学校读者我要写书评

暂无评论

Efficient Dual-Confounding Eliminating for Weakly-supervised Temporal Action Localization 24

Efficient Dual-Confounding Eliminating for Weakly-supervised...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Ao Liu, Huijun Sheng, Jinrong Chen, Zhongming Ge, Yongxin School of Big Data and Software Engineering Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China

ISBN: (纸本)9798400706868

Weakly-supervised Temporal Action Localization (WTAL) following a localization-by-classification paradigm has achieved significant results, yet still grapples with confounding arising from ambiguous snippets. Previous works have attempted to distinguish these ambiguous snippets from action snippets without investigating the underlying causes of their formation, thus failing to effectively eliminate the bias on both action-context and action-content. In this paper, we revisit WTAL from the perspective of structural causal model to identify the true origins of confounding, and propose an efficient dual-confounding eliminating framework to alleviate these biases. Specifically, we construct a Substituted Confounder Set (SCS) to eliminate the confounding bias on action-context by leveraging the modal disparity between RGB and FLOW. Then, a Multi-level Consistency Mining (MCM) method is designed to mitigate the confounding bias on action-content by utilizing the consistency between discriminative snippets and corresponding proposals at both the feature and label levels. Notably, SCS and MCM could be seamlessly integrated into any two-stream models without additional parameters by Expectation-Maximization (EM) algorithm. Extensive experiments on two challenging benchmarks including THUMOS14 and ActivityNet-1.2 demonstrate the superior performance of our method. © 2024 ACM.

关键词： Expectation maximization algorithm

来源：评论

学校读者我要写书评

暂无评论

ScanTrimmer: an Online Dynamic Objects Removal Framework in Laser Scan for Robust Localization

ScanTrimmer: an Online Dynamic Objects Removal Framework in ...

引用

2023 IEEE International Conference on Robotics and Biomimetics, ROBIO 2023

作者： Wang, Jing Duan, Yifan Ji, Jianmin University of Science and Technology of China School of Data Science Hefei230026 China University of Science and Technology of China School of Computer Science and Technology Hefei230026 China

ISBN: (纸本)9798350325706

The Simultaneous Localization and Mapping (SLAM) technique is often employed in robotic localization tasks. For lidar-based SLAM, point cloud registration (PCR) is one of the crucial factors for overall localization precision. However, the quality of point-to-point correspondence between two distinct point clouds obtained by PCR is environment dependent. Particularly in dynamic environments, the movement of objects can disrupt this correspondence, resulting in a degradation of localization accuracy. Therefore, previous SLAM methods often fail in environments with ample dynamic objects. Intuitively, we can remove dynamic points from the input laser scan to degenerate the influence of environment dynamicity. However, identifying dynamic objects precisely from point clouds which is challenging for the SLAM running in robotic systems with high real-time requirements. This paper proposes a new online lidar-based SLAM framework, i.e., ScanTrimmer, which significantly enhances the localization accuracy of the SLAM systems by detecting and deleting potential dynamic points through space-based comparison in point cloud distribution between scans taken at a specific interval. The experiments demonstrate that ScanTrimmer can improve the localization accuracy by 44.69% on the simulated dataset and 25.99% on the real-world dataset compared with the previous method. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attribute-based Message Recovery Designated Verifier Proxy Signature Scheme in Telemedicine System

Journal of Network Intelligence

引用

Journal of Network Intelligence 2022年第1期7卷 101-113页

作者： Hu, Yu Zhang, Yi-Fan Huang, Hui Zhou, Yu-Ping School of Computer Science Minnan Normal University Zhangzhou363000 China School of Computer Science Minnan Normal University Key Laboratory of Data Science and Intelligence Application Fujian Province University Zhangzhou363000 China

With the promotion of cloud medical diagnostic applications, the telemedicine system has become increasingly mature, which brings about much convenience to the people’s lives. Meanwhile, the diagnostic time was greatly reduced. Due to telemedicine system usually involves the sensitive information of users, the privacy issue is urgently to be solved. In order to solve the above problem, an attribute-based designated verifier proxy signature scheme, combined with message recovery, is proposed for the telemedicine system. A proxy delegation is designed to allow the proxy signer to obtain the same signing capacity as the original signer, the attribute-based fine-grained access control is also present to enable the valid verification of the signature and recovery of data. In addition, the scheme achieves unforgeability of signature and can resist the chosen message attack in Random Oracle Model. The comparisons of performance analysis demonstrates that the scheme is efficient in signing and verification phases. Therefore, it could be well appropriate for telemedicine system. © 2022, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Diagnosis

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：