检索结果-内蒙古大学图书馆

OpenVNA: A Framework for Analyzing the Behavior of Multimodal Language Understanding System under Noisy Scenarios

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yuan, Ziqi Zhang, Baozheng Xu, Hua Liang, Zhiyun Gao, Kai State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University China China School of Information Science and Engineering Hebei University of Science and Technology China College of Information and Electrical Engineering China Agricultural University China Technology Development Co. Ltd. China

We present OpenVNA, an open-source framework designed for analyzing the behavior of multimodal language understanding systems under noisy conditions. OpenVNA serves as an intuitive toolkit tailored for researchers, facilitating convenience batch-level robustness evaluation and on-the-fly instance-level demonstration. It primarily features a benchmark Python library for assessing global model robustness, offering high flexibility and extensibility, thereby enabling customization with user-defined noise types and models. Additionally, a GUI-based interface has been developed to intuitively analyze local model behavior. In this paper, we delineate the design principles and utilization of the created library and GUI-based web platform. Currently, OpenVNA is publicly accessible at https://***/thuiar/OpenVNA, with a demonstration video available at https://***/0Z9cW7RGct4. © 2024, CC BY-NC-SA.

关键词： Graphical user interfaces

LFNAT 2023 Challenge on Light Field Depth Estimation: Methods and Results

学校读者我要写书评

暂无评论

LFNAT 2023 Challenge on Light Field Depth Estimation: Method...

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Hao Sheng Yebin Liu Jingyi Yu Gaochang Wu Wei Xiong Ruixuan Cong Rongshan Chen Longzhao Guo Yanlin Xie Shuo Zhang Song Chang Youfang Lin Wentao Chao Xuechun Wang Guanghui Wang Fuqing Duan Tun Wang Da Yang Zhenglong Cui Sizhe Wang Mingyuan Zhao Qiong Wang Qianyu Chen Zhengyu Liang Yingqian Wang Jungang Yang Xueting Yang Junli Deng LFNAT 2023 Challenge State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University and Beihang Hangzhou Innovation Institute Yuhang

This paper reviews the 1st LFNAT challenge on light field depth estimation, which aims at predicting disparity information of central view image in a light field (i.e., pixel offset between central view image and adjacent view image). Compared to multi-view stereo matching, light field depth estimation emphasizes efficient utilization of the 2D angular information from multiple regularly varying views. This challenge specifies UrbanLF [20] light field dataset as the sole data source. There are two phases in total: submission phase and final evaluation phase, in which 75 registered participants successfully submit their predicted results in the first phase and 7 eligible teams compete in the second phase. The performance of all submissions is carefully reviewed and shown in this paper as a new standard for the current state-of-the-art in light field depth estimation. Moreover, the implementation details of these methods are also provided to stimulate related advanced research.

关键词：

Ciphertext-only fault analysis on the Midori lightweight cryptosystem

学校读者我要写书评

暂无评论

science China(Information sciences) 2020年第3期63卷 288-292页

作者： Wei LI Linfeng LIAO Dawu GU Shan CAO Yixin WU Jiayao LI Zhihong ZHOU Zheng GUO Ya LIU Zhiqiang LIU School of Computer Science and Technology Donghua University Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai Key Laboratory of Scalable Computing and Systems Shanghai Key Laboratory of Integrate Administration Technologies for Information Security School of Microelectronics Shanghai Jiao Tong University Department of Computer Science and Engineering University of Shanghai for Science and Technology

Dear editor,The Midori lightweight cipher can be applied in the RFID tags and other low-resource devices to protect information on the Internet. This cipher was proposed by Banik et al. and presented at the ASIACRYPT conference [1]. It has a Substitution Permutation Network structure with a 128-bit keysize, and two block-size variants, 64 bits

关键词： CFA Ciphertext-only fault analysis on the Midori lightweight cryptosystem

State Derivative Normalization for Continuous-Time Deep Neural Networks

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第15期58卷 253-258页

作者： Jonas Weigand Gerben I. Beintema Jonas Ulmen Daniel Görges Roland Tóth Maarten Schoukens Martin Ruskowski Chair of Machine Tools and Control Systems RPTU Kaiserslautern and the German Research Center for Artificial Intelligence Kaiserslautern Germany Control Systems (CS) Group at the Department of Electrical Engineering Eindhoven University of Technology Netherlands. R. Tóth is also affiliated to the Systems and Control Laboratory at the Institute for Computer Science and Control Budapest Hungary Institute for Electromobility RPTU Kaiserslautern Germany

The importance of proper data normalization for deep neural networks is well known. However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature.

关键词： System Identification Continuous-Time Neural Ordinary Differential Equations Nonlinear State-Space

Robustness-Eva-MRC: Assessing and Analyzing the Robustness of Neural Models in Extractive Machine Reading Comprehension

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Fang, Jingliang Xu, Hua Wu, Zhijing Gao, Kai Che, Xiaoyin Hui, Haotian State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China School of Information Science and Engineering Hebei University of Science and Technology China Siemens AG Beijing China

Deep neural networks, despite their remarkable success in various language understanding tasks, have been found vulnerable to adversarial attacks and subtle input perturbations, revealing a robustness shortfall. To explore this, this paper presents Robustness-Eva-MRC, an interactive platform designed to assess and analyze the robustness of pre-trained and large-scale language models in extractive machine reading comprehension (MRC) tasks. The platform integrates eight adversarial attack methods across character-, word-, and sentence-levels, and applies them to five MRC datasets, thereby fabricating challenging adversarial testing sets. Then it evaluates the MRC models on both original and adversarial sets, yielding insights into their robustness through performance gaps. Moreover, Robustness-Eva-MRC provides comprehensive visualizations and detailed case studies, enhancing the understanding of model robustness. A screencast video and additional material are available at https://***/distantJing/Robustness-Eva-MRC. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

On Shaping Gain of Multidimensional Constellation in Linear and Nonlinear Optical Fiber Channel

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Bin Liang, Zhiwei Lei, Yi Deng, JingXin Li, Shen Liga, Gabriele School of Computer Science and Information Engineering Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province China Department of Electrical Engineering Chalmers University of Technology Gothenburg Sweden Department of Electrical and Computer Engineering Université Laval Québec Canada Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands

Utilizing the multi-dimensional (MD) space for constellation shaping has been proven to be an effective approach for achieving shaping gains. Despite there exists a variety of MD modulation formats tailored for specific optical transmission scenarios, there remains a notable absence of a dependable comparison method for efficiently and promptly re-evaluating their performance in arbitrary transmission systems. In this paper, we introduce an analytical nonlinear interference (NLI) power model-based shaping gain estimation method to enable a fast performance evaluation of various MD modulation formats in coherent dual-polarization (DP) optical transmission system. In order to extend the applicability of this method to a broader set of modulation formats, we extend the established NLI model to take the 4D joint distribution into account and thus able to analyze the complex interactions of non-iid signaling in DP systems. With the help of the NLI model, we conduct a comprehensive analysis of the state-of-the-art modulation formats and investigate their actual shaping gains in two types of optical fiber communication scenarios (multi-span and single-span). The numerical simulation shows that for arbitrary modulation formats, the NLI power and relative shaping gains in terms of signal-to-noise ratio can be more accurately estimated by capturing the statistics of MD symbols. Furthermore, the proposed method further validates the effectiveness of the reported NLI-tolerant modulation format in the literature, which reveals that the linear shaping gains and modulation-dependent NLI should be jointly considered for nonlinearity mitigation. © 2024, CC BY-NC-SA.

关键词： Optical fibers

DDPS: Dynamic Differential Pricing-based Edge Offloading System with Energy Harvesting Devices

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xue, Hai Xia, Yun Xiong, Neal N. Zhang, Di Pei, Songwen School of Optical- Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China Department of Computer Science and Mathematics Sul Ross State University AlpineTX79830 United States School of Electrical and Information Engineering Zhengzhou University the Henan International Joint Laboratory of Intelligent Health Information System the National Telemedicine Center National Engineering Laboratory for Internet Medical Systems and Applications Zhengzhou450001 China

Mobile edge computing (MEC) paves the way to alleviate the burden of energy and computation of mobile users (MUs) by offloading tasks to the network edge. To enhance the MEC server utilization by optimizing its resource allocation, a well-designed pricing strategy is indispensable. In this paper, we consider the edge offloading scenario with energy harvesting devices, and propose a dynamic differential pricing system (DDPS), which determines the price per unit time according to the usage of computing resources to improve the edge server utilization. Firstly, we propose an offloading decision algorithm to decide whether to conduct the offloading operation and how much data to be offloaded if conducted, the algorithm determines offloading operation by balancing the energy harvested with the energy consumed. Secondly, for the offloading case, we formulate the game between the MUs and the server as a Stackelberg game, and propose a differential pricing algorithm to determine the optimal computing resources required by MUs. Furthermore, the proposed algorithm also reallocates computing resources for delay-sensitive devices while server resources are surplus after the initial allocation, aiming to make full use of the server computing resources. Extensive simulations are conducted to demonstrate the effectiveness of the proposed DDPS scheme. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

Graph Prompt Learning: A Comprehensive Survey and Beyond

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Sun, Xiangguo Zhang, Jiawen Wu, Xixi Cheng, Hong Xiong, Yun Li, Jia Department of Systems Engineering and Engineering Management Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong Hong Kong University of Science and Technology Guangzhou China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

Artificial General Intelligence (AGI) has revolutionized numerous fields, yet its integration with graph data, a cornerstone in our interconnected world, remains nascent. This paper presents a pioneering survey on the emerging domain of graph prompts in AGI, addressing key challenges and opportunities in harnessing graph data for AGI applications. Despite substantial advancements in AGI across natural language processing and computer vision, the application to graph data is relatively underexplored. This survey critically evaluates the current landscape of AGI in handling graph data, highlighting the distinct challenges in cross-modality, cross-domain, and cross-task applications specific to graphs. Our work is the first to propose a unified framework for understanding graph prompt learning, offering clarity on prompt tokens, token structures, and insertion patterns in the graph domain. We delve into the intrinsic properties of graph prompts, exploring their flexibility, expressiveness, and interplay with existing graph models. A comprehensive taxonomy categorizes over 100 works in this field, aligning them with pre-training tasks across node-level, edge-level, and graph-level objectives. Additionally, we present, ProG, a Python library, and an accompanying website, to support and advance research in graph prompting. The survey culminates in a discussion of current challenges and future directions, offering a roadmap for research in graph prompting within AGI. Through this comprehensive analysis, we aim to catalyze further exploration and practical applications of AGI in graph data, underlining its potential to reshape AGI fields and beyond. ProG and the website can be accessed by https: //***/WxxShirley/Awesome-Graph-Prompt, and https://***/sheldonresearch/ProG, respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： Websites

Continual Reinforcement Learning for Digital Twin Synchronization Optimization

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile Computing 2025年

作者： Tong, Haonan Chen, Mingzhe Zhao, Jun Hu, Ye Yang, Zhaohui Liu, Yuchen Yin, Changchuan Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence Beijing Advanced Information Network Laboratory Beijing China College of Computing and Data Science Singapore University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral Gables33146 United States University of Miami Department of Industrial and Systems Engineering Coral Gables33146 United States Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China North Carolina State University Department of Computer Science RaleighNC27695 United States Beijing Key Laboratory of Network System Architecture and Convergence China Beijing University of Posts and Telecommunications Beijing Advanced Information Network Laboratory Beijing100876 China

This article investigates the adaptive resource allocation scheme for digital twin (DT) synchronization optimization over dynamic wireless networks. In our considered model, a base station (BS) continuously collects factory physical object state data from wireless devices to build a real-time virtual DT system for factory event analysis. Due to continuous data transmission, maintaining DT synchronization must use extensive wireless resources. To address this issue, a subset of devices is selected to transmit their sensing data, and resource block (RB) allocation is optimized. This problem is formulated as a constrained Markov process (CMDP) problem that minimizes the long-term mismatch between the physical and virtual systems. To solve this CMDP, we first transform the problem into a dual problem that refines RB constraint impacts on device scheduling strategies. We then propose a continual reinforcement learning (CRL) algorithm to solve the dual problem. The CRL algorithm learns a stable policy across historical experiences for quick adaptation to dynamics in physical states and network capacity. Simulation results show that the CRL can adapt quickly to network capacity changes and reduce normalized root mean square error (NRMSE) between physical and virtual states by up to 55.2%, using the same RB number as traditional methods. © 2025 IEEE. All rights reserved.

关键词： Markov processes