检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Xiaogeng Li, Minghui Wang, Haoyu Hu, Shengshan Ye, Dengpan Jin, Hai Wu, Libing Xiao, Chaowei School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab China School of Cyber Science and Engineering Wuhan University China Arizona State University United States

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo)1, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Graft: Efficient Inference Serving for Hybrid Deep Learning with SLO Guarantees via DNN Re-alignment

arXiv

引用

arXiv 2023年

作者： Wu, Jing Wang, Lin Jin, Qirui Liu, Fangming The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab in The School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Peng Cheng Laboratory Huazhong University of Science and Technology China

Deep neural networks (DNNs) have been widely adopted for various mobile inference tasks, yet their ever-increasing computational demands are hindering their deployment on resource-constrained mobile devices. Hybrid deep learning partitions a DNN into two parts and deploys them across the mobile device and a server, aiming to reduce inference latency or prolong battery life of mobile devices. However, such partitioning produces (non-uniform) DNN fragments which are hard to serve efficiently on the server. This paper presents Graft—an efficient inference serving system for hybrid deep learning with latency service-level objective (SLO) guarantees. Our main insight is to mitigate the non-uniformity by a core concept called DNN re-alignment, allowing multiple heterogeneous DNN fragments to be restructured to share layers. To fully exploit the potential of DNN re-alignment, Graft employs fine-grained GPU resource sharing. Based on that, we propose efficient algorithms for merging, grouping, and re-aligning DNN fragments to maximize request batching opportunities, minimizing resource consumption while guaranteeing the inference latency SLO. We implement a Graft prototype and perform extensive experiments with five types of widely used DNNs and real-world network traces. Our results show that Graft improves resource efficiency by up to 70% compared with the state-of-the-art inference serving systems. © 2023, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

SLMP: A Scientific Literature Management Platform Based on Large Language Models

SLMP: A Scientific Literature Management Platform Based on L...

引用

IEEE International Conference on big Knowledge (ICBK)

作者： Menghao Guo Jinling Jiang Fan Wu Shanxin Sun Chen Zhang Wenhui Li Zeyi Sun Guangyong Chen Xindong Wu Research Center for Life Sciences Computing Zhejiang Lab Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China Key Laboratory of Knowledge Engineering With Big Data Hefei University of Technology Hefei China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

This paper presents a Scientific Literature Management Platform (SLMP, demo link 1 ) based on large language models (LLMs). The platform consists of four modules: literature management, literature extraction, literature retrieval, and question answering. The core techniques used to support the four modules across the platform include a fine-tuned model PaperExtractGPT and a continual pre-training model ChatPaperGPT based on ChatGLM 2 using the data from scientific research literature, responsible for information extraction and communication, respectively. Due to their powerful capabilities in natural language understanding and generation, LLMs can understand complex scientific concepts based on the provided contexts, and thus generate high-quality texts and conduct in-depth information retrieval and question answering. Our platform can help researchers manage and utilize literature more effectively and efficiently for finding relevant literature, obtaining required information, and generating new knowledge.

关键词： Training Large language models Knowledge graphs Information retrieval data models Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

Towards Open-Set Document Layout Segmentation Through Class-Specific Prototype Learning

SSRN

引用

SSRN 2023年

作者： Sang, Yuman Yu, Shenbao Zeng, Yifeng Pan, Yinghui Yao, Zhangrui Department of Automation Xiamen University Xiamen China Department of Computer and Information Sciences Northumbria University Newcastle upon Tyne United Kingdom National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Open-set segmentation is an emerging and challenging topic, especially when it is combined with domain-specific tasks. Beyond recognizing known classes, the system needs to reject the unknowns. In this paper, we study the open-set document layout segmentation problem and propose a two-phase framework (OpenDLS) that accurately recognizes pixels in document images from known classes and rejects those from the unknowns. In the first phase, we propose a class-specific prototype learning strategy and design two loss functions for model training. In addition, considering the multifarious appearance of objects, a multi-scale feature fusion module is developed. In the second phase, we propose three rejection rules to detect the pixels that belong to unknown classes. To the best of our knowledge, this is the first work to investigate the open-set document layout segmentation task. Extensive experiments demonstrate the effectiveness of our framework in both known class classification and unknown class identification. © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Robin: A Novel Method to Produce Robust Interpreters for Deep Learning-Based Code Classifiers

arXiv

引用

arXiv 2023年

作者： Li, Zhen Zhang, Ruqian Zou, Deqing Wang, Ning Li, Yating Xu, Shouhuai Chen, Chen Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Colorado Colorado Springs United States Center for Research in Computer Vision University of Central Florida United States School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier;the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach

arXiv

引用

arXiv 2024年

作者： Tang, Xin Chen, Qian Weng, Wenjie Liao, Binhan Wang, Jiacheng Cao, Xianbin Li, Xiaohuan Guangxi University Key Laboratory of Intelligent Networking and Scenario System School of Information and Communication Guilin University of Electronic Technology Guilin541004 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Architecture and Transportation Engineering Guilin University of Electronic Technology Guilin541004 China National Engineering Laboratory for Comprehensive Transportation Big Data Application Technology Guangxi Nanning530001 China College of Computing and Data Science Nanyang Technological University 639798 Singapore School of Electronic and Information Engineering The Key Laboratory of Advanced Technology of Near Space Information System Ministry of Industry and Information Technology of China Beihang University Beijing100191 China

Unmanned Aerial Vehicles (UAVs) possess high mobility and flexible deployment capabilities, prompting the development of UAVs for various application scenarios within the Internet of Things (IoT). The unique capabilities of UAVs give rise to increasingly critical and complex tasks in uncertain and potentially harsh environments. The substantial amount of data generated from these applications necessitates processing and analysis through deep neural networks (DNNs). However, UAVs encounter challenges due to their limited computing resources when managing DNN models. This paper presents a joint approach that combines multiple-agent reinforcement learning (MARL) and generative diffusion models (GDM) for assigning DNN tasks to a UAV swarm, aimed at reducing latency from task capture to result output. To address these challenges, we first consider the task size of the target area to be inspected and the shortest flying path as optimization constraints, employing a greedy algorithm to resolve the subproblem with a focus on minimizing the UAV’s flying path and the overall system cost. In the second stage, we introduce a novel DNN task assignment algorithm, termed GDM-MADDPG, which utilizes the reverse denoising process of GDM to replace the actor network in multi-agent deep deterministic policy gradient (MADDPG). This approach generates specific DNN task assignment actions based on agents’ observations in a dynamic environment. Simulation results indicate that our algorithm performs favorably compared to benchmarks in terms of path planning, Age of Information (AoI), energy consumption, and task load balancing. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning

arXiv

引用

arXiv 2024年

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. Copyright © 2024, The Authors. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration

arXiv

引用

arXiv 2024年

作者： Cheng, Xinxing Jia, Xi Lu, Wenqi Li, Qiufu Shen, Linlin Krull, Alexander Duan, Jinming School of Computer Science University of Birmingham BirminghamB15 2TT United Kingdom Department of Computing and Mathematics Manchester Metropolitan University ManchesterM15 6BH United Kingdom National Engineering Laboratory for Big Data System Computing Technology Shenzhen University 518060 China

Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. However, due to the cascaded nature and repeated composition/warping operations on feature maps, these methods negatively increase memory usage during training and testing. Moreover, such approaches lack explicit constraints on the learning process of small deformations at different scales, thus lacking explainability. In this study, we introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales, utilizing the wavelet coefficients derived from the original input image pair. By exploiting the properties of the wavelet transform, these estimated coefficients facilitate the seamless reconstruction of a full-resolution displacement/velocity field via our devised inverse discrete wavelet transform (IDWT) layer. This approach avoids the complexities of cascading networks or composition operations, making our WiNet an explainable and efficient competitor with other coarse-to-fine methods. Extensive experimental results from two 3D datasets show that our WiNet is accurate and GPU efficient. Code is available at https://***/x-xc/WiNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

CPSAA: Accelerating Sparse Attention using Crossbar-based Processing-In-Memory Architecture

arXiv

引用

arXiv 2022年

作者： Li, Huize Jin, Hai Zheng, Long Liao, Xiaofei Huang, Yu Liu, Cong Xu, Jiahong Duan, Zhuohui Chen, Dan Gui, Chuangyi 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 Wuhan China

The attention-based neural network attracts great interest due to its excellent accuracy enhancement. However, the attention mechanism requires huge computational efforts to process unnecessary calculations, significantly limiting the system’s performance. To reduce the unnecessary calculations, researchers propose sparse attention to convert some dense-dense matrices multiplication (DDMM) operations to sampled dense-dense matrix multiplication (SDDMM) and sparse matrix multiplication (SpMM) operations. However, current sparse attention solutions introduce massive off-chip random memory access since the sparse attention matrix is generally unstructured. We propose CPSAA, a novel crossbar-based processing-in-memory (PIM)-featured sparse attention accelerator to eliminate off-chip data transmissions. First, we present a novel attention calculation mode to balance the crossbar writing and crossbar processing latency. Second, we design a novel PIM-based sparsity pruning architecture to eliminate the pruning phase’s off-chip data transfers. Finally, we present novel crossbar-based SDDMM and SpMM methods to process unstructured sparse attention matrices by coupling two types of crossbar arrays. Experimental results show that CPSAA has an average of 89.6×, 32.2×, 17.8×, 3.39×, and 3.84× performance improvement and 755.6×, 55.3×, 21.3×, 5.7×, and 4.9× energy-saving when compare with GPU, FPGA, SANGER, ReBERT, and ReTransformer. Copyright © 2022, The Authors. All rights reserved.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of Multi-tiered Heterogeneous Memory Architecture

Design and Simulation of Multi-tiered Heterogeneous Memory A...

引用

International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication systems (MASCOTS)

作者： Jinyuan Hu Haikun Liu Hai Jin Xiaofei Liao 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 Wuhan China

Heterogeneous memory systems have become increasingly popular in recent years. Because heterogeneous storage media often show significantly different characteristics in terms of bandwidth, latency, capacity, and energy consumption, it is still challenging to best utilize them for cost-efficient and energy-efficient heterogeneous memory systems. In this paper, we propose a simulation framework for multi-tiered heterogeneous memory architectures based on GEM5 and DRAMsim3 simulators. We design a heterogeneous memory controller to architect Non-Volatile Memory (NVM) as main memory, and architect both Dynamic Random Access Memory (DRAM) and High-Bandwidth Memory (HBM) as a hybrid cache of NVM. Specifically, HBM, DRAM, and NVM are managed in a single (flat) address space. However, we use an address remapping table to maintain the mappings between NVM pages and HBM/DRAM pages, and logically manage HBM/DRAM/NVM as a three-tiered hybrid memory system. We also design a hardware-supported hot page monitor based on Majority Element Algorithm (MEA) to identify the hottest pages in the DRAM, and a dynamic threshold adjustment scheme for hot page migration to balance the memory bandwidth between DRAM and HBM. Our multi-tiered heterogeneous memory architecture can take advantage of the large capacity of NVM, the low latency of DRAM, and the high bandwidth of HBM concurrently. Experimental results show that our tiered memory architecture can improve application performance by an average of $2.5\times$ compared with an NVM-only architecture, and up to 57.4% compared with a DRAM-only architecture. Moreover, the performance gap between our HBM/DRAM/NVM architecture and a HBM-only architecture is less than 10%.

关键词： Analytical models Nonvolatile memory Heuristic algorithms Computational modeling Memory architecture Random access memory Computer architecture

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：