检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Li, Hengzhuang Zhang, Teng National Engineering Research Center for Big Data Technology and System Service Computing Technology and Systems Laboratory Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

Out-of-distribution (OOD) detection is crucial for developing trustworthy and reliable machine learning systems. Recent advances in training with auxiliary OOD data demonstrate efficacy in enhancing detection capabilities. Nonetheless, these methods heavily rely on acquiring a large pool of high-quality natural outliers. Some prior methods try to alleviate this problem by synthesizing virtual outliers but suffer from either poor quality or high cost due to the monotonous sampling strategy and the heavy-parameterized generative models. In this paper, we overcome all these problems by proposing the Hamiltonian Monte Carlo Outlier Synthesis (HamOS) framework, which views the synthesis process as sampling from Markov chains. Based solely on the in-distribution data, the Markov chains can extensively traverse the feature space and generate diverse and representative outliers, hence exposing the model to miscellaneous potential OOD scenarios. The Hamiltonian Monte Carlo with sampling acceptance rate almost close to 1 also makes our framework enjoy great efficiency. By empirically competing with SOTA baselines on both standard and large-scale benchmarks, we verify the efficacy and efficiency of our proposed HamOS. Our code is available at: https://***/Fir-lat/HamOS_OOD. © 2025, CC BY.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

Penta-Encoder with Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation 17

Penta-Encoder with Medical Transformer for Incomplete Multim...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Yu, Guohui Wang, Lihui Chen, Qijian Wang, Li Tang, Kun Cheng, Xinyu Zhu, Yuemin Guizhou University Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Univ Lyon Insa Lyon Cnrs Inserm Creatis Umr 5220 U1206 Lyon France

ISBN: (纸本)9798350387384

Accurate brain tumor segmentation of magnetic resonance imaging (MRI) images requires the integration of multimodal data in effective collaborative learning. However, clinical scenarios often face missing modalities, significantly impacting segmentation performance. In this paper, we propose the penta-encoder with medical transformer (Penta-MedTrans) for incomplete multimodal learning, which consists of four main components: a modality-specific encoder (MSE), a modality-dynamic encoder (MDE), a multimodal fusion module (MMFM) and a convolutional decoder. The MSE extracts unique features for each modality, while the MDE captures inter-modal semantics to address missing modalities. The MMFM establishes and aligns long-range correlations between modal-invariant features and global semantics of tumor regions. The convolutional decoder generates robust segmentation results by progressively upsampling and fusing modality-invariant features. We extensively validated our method on the BraTS 2020 and BraTS 2021 datasets for brain tumor segmentation. Results showed that our method outperforms SOTA for incomplete multimodal brain tumor segmentation across most subsets. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

FlexiFed: Personalized Federated Learning for Edge Clients with Heterogeneous Model Architectures 23

FlexiFed: Personalized Federated Learning for Edge Clients w...

引用

2023 World Wide Web Conference, WWW 2023

作者： Wang, Kaibin He, Qiang Chen, Feifei Chen, Chunyang Huang, Faliang Jin, Hai Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia Faculty of Information Technology Monash University Australia Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed;and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×. © 2023 ACM.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Self-supervised fast reconstruction method for diffusion MRI based on multi-directional assistance 17

Self-supervised fast reconstruction method for diffusion MRI...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Wu, Yuxin Zhang, Jian Wang, Lihui Cao, Ying Wu, Linhai Wu, Yunjia Ye, Chen Zhu, Yuemin Guizhou University Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China Univ Lyon Insa Lyon Cnrs Inserm Creatis Umr 5220 U1206 France

ISBN: (纸本)9798350387384

Diffusion MRI (dMRI) is widely used for the detection and diagnosis of various pathologies due to its non-invasive nature. However, its signal acquisition process is relatively slow and susceptible to motions. In order to accelerate reconstruction process, many deep learning-based methods have been developed in recent years to achieve promising results, while most of them are supervised based methods and require fully sampled data which are difficult to obtain in practical applications to train the network. Self-supervised based methods were proposed to deal with this problem to a certain extent, however, they are devoted only to conventional MRI data, ignoring the correlation between the directions of dMRI data. To address this issue, we propose a self-supervised fast reconstruction method for dMRI based on multi-directional assistance. The method better utilizes the information between dMRI data directions by Partition-Replace operation, cleverly constructing data pairs and designing effective self-supervised strategy for bi-directional prediction, which can overcome the problem of data incompleteness and guide the model to reconstruct unsampled signals in spite of the difficulty of acquiring fully sampled data. Experimental results show that our method achieves better reconstruction in the absence of fully sampled data, even with an 8-fold acceleration factor. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fooling the Textual Fooler via Randomizing Latent Representations

arXiv

引用

arXiv 2023年

作者： Hoang, Duy C. Nguyen, Quang H. Manchanda, Saurav Peng, MinLong Wong, Kok-Seng Doan, Khoa D. College of Engineering and Computer Science VinUniversity Viet Nam Amazon United States Cognitive Computing Lab Baidu Research China

Despite outstanding performance in a variety of Natural Language Processing (NLP) tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Several attacks can even compromise the model without requiring access to the model architecture or model parameters (i.e., a black-box setting), and thus are detrimental to existing NLP applications. To perform these attacks, the adversary queries the victim model many times to determine the most important parts in an input text and transform. In this work, we propose a lightweight and attack-agnostic defense whose main goal is to perplex the process of generating an adversarial example in these query-based black-box attacks;that is to fool the textual fooler. This defense, named AdvFooler, works by randomizing the latent representation of the input at inference time. Different from existing defenses, AdvFooler does not necessitate additional computational overhead during training nor does it rely on assumptions about the potential adversarial perturbation set while having a negligible impact on the model’s accuracy. Our theoretical and empirical analyses highlight the significance of robustness resulting from confusing the adversary via randomizing the latent space, as well as the impact of randomization on clean accuracy. Finally, we empirically demonstrate near state-of-the-art robustness of AdvFooler against representative adversarial attacks on two benchmark datasets. Code for AdvFooler is available at: https://***/mail-research/ AdvFooler-text-defender Copyright © 2023, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Ethereum smart contract security research:survey and future research opportunities

引用

Frontiers of Computer science 2021年第2期15卷 143-160页

作者： Zeli WANG Hai JIN Weiqi DAI Kim-Kwang Raymond CHOO Deqing ZOU National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabHubei Engineering Research Center on Big Data SecurityWuhan430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan430074China School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan430074China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518057China Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Blockchain has recently emerged as a research trend,with potential applications in a broad range of industries and *** particular successful Blockchain technology is smart contract,which is widely used in commercial settings(e.g.,high value financial transactions).This,however,has security implications due to the potential to financially benefit from a security incident(e.g.,identification and exploitation of a vulnerability in the smart contract or its implementation).Among,Ethereum is the most active and ***,in this paper,we systematically review existing research efforts on Ethereum smart contract security,published between 2015 and ***,we focus on how smart contracts can be maliciously exploited and targeted,such as security issues of contract program model,vulnerabilities in the program and safety consideration introduced by program execution *** also identify potential research opportunities and future research agenda.

关键词： smart contract security blockchain vulnerability unreliable data

来源：评论

学校读者我要写书评

暂无评论

Software-Defined, Fast and Strongly-Consistent data Replication for RDMA-Based PM datastores

Software-Defined, Fast and Strongly-Consistent Data Replicat...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Haodi Lu Haikun Liu Chencheng Ye Xiaofei Liao Fubing Mao Yu Zhang Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computing Science and Technology Huazhong University of Science and Technology China

Modern storage systems typically replicate data on multiple servers to provide high reliability and availability. However, most commercially-deployed datastores often fail to offer low latency, high throughput, and strong consistency at the same time. This paper presents Whale, a Remote Direct Memory Access (RDMA) based primary-backup replication system for in-memory datastores. Whale achieves both low latency and strong consistency by decoupling metadata multicasting from data replication for all backup nodes, and using an optimistic commitment mechanism to respond to client write requests earlier. Whale achieves high throughput by propagating writes from the primary node to backup nodes asynchronously via RDMA-optimized chain replication. To further reduce the cost of data replication, we design a log-structured datastore to fully exploit the advantages of one-sided RDMA and Persistent Memory (PM). We implement Whale on a cluster equipped with PM and InfiniBand RDMA networks. Experimental results show that Whale achieves much higher throughput and lower latency than state-of-the-art replication protocols.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fine-Grained Quantitative Emotion Editing for Speech Generation

Fine-Grained Quantitative Emotion Editing for Speech Generat...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Sho Inoue Kun Zhou Shuai Wang Haizhou Li School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Speech Lab Institute for Intelligent Computing Alibaba Group Singapore

ISBN: (数字)9798350367331

ISBN: (纸本)9798350367348

It remains a significant challenge how to quantitatively control the expressiveness of speech emotion in speech generation. In this work, we propose an approach for quantitative manipulation of the emotion rendering for emotion editing in speech generation. We apply a hierarchical emotion distribution extractor, i.e. Hierarchical ED, that quantifies the intensity of emotions at different levels of granularity. Hierarchical ED is subsequently integrated into the FastSpeech2 framework, guiding the model to learn emotion intensity at phoneme, word, and utterance levels. During synthesis, users can manually edit the emotional intensity of the generated voices. Both objective and subjective evaluations demonstrate the effectiveness of the proposed network in terms of fine-grained quantitative emotion editing.

关键词： Asia Information processing Rendering (computer graphics) Text to speech Speech processing

来源：评论

学校读者我要写书评

暂无评论

Hanging Around: cognitive Inspired Reasoning for Reactive Robotics 14

Hanging Around: Cognitive Inspired Reasoning for Reactive Ro...

引用

14th International Conference on Formal Ontology in Information Systems, FOIS 2024

作者： Pomarlan, Mihai de Giorgis, Stefano Ringe, Rachel Hedblom, Maria M. Tsiogkas, Nikolaos Applied Linguistics Department University of Bremen Bremen Germany Institute of Cognitive Sciences and Technologies National Research Council Catania Italy Digital Media Lab University of Bremen Bremen Germany Department of Computing Jönköping School of Engineering Jönköping Sweden Department of Computer Science KU Leuven Leuven Belgium

ISBN: (纸本)9781643685618

Situationally-aware artificial agents operating with competence in natural environments face several challenges: spatial awareness, object affordance detection, dynamic changes and unpredictability. A critical challenge is the agent’s ability to identify and monitor environmental elements pertinent to its objectives. Our research introduces a neurosymbolic modular architecture for reactive robotics. Our system combines a neural component performing object recognition over the environment and image processing techniques such as optical flow, with symbolic representation and reasoning. The reasoning system is grounded in the embodied cognition paradigm, via integrating image schematic knowledge in an ontological structure. The ontology is operatively used to create queries for the perception system, decide on actions, and infer entities’ capabilities derived from perceptual data. The combination of reasoning and image processing allows the agent to focus its perception for normal operation as well as discover new concepts for parts of objects involved in particular interactions. The discovered concepts allow the robot to autonomously acquire training data and adjust its subsymbolic perception to recognize the parts, as well as making planning for more complex tasks feasible by focusing search on those relevant object parts. We demonstrate our approach in a simulated world, in which an agent learns to recognize parts of objects involved in support relations. While the agent has no concept of handle initially, by observing examples of supported objects hanging from a hook it learns to recognize the parts involved in establishing support and becomes able to plan the establishment/destruction of the support relation. This underscores the agent’s capability to expand its knowledge through observation in a systematic way, and illustrates the potential of combining deep reasoning with reactive robotics in dynamic settings. © 2024 The Authors.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based data Sharing Framework for Malaysia Government Aid Management System

Blockchain-based Data Sharing Framework for Malaysia Governm...

引用

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Azmi, Azman Yahya, Farashazillah Moung, Ervin Gubin Sallehudin, Hasimi Utomo, Rio Guntur Azman, Nur Afrina Universiti Malaysia Sabah Advanced Machine Intelligence Research Lab Faculty of Computing and Informatics Sabah Kota Kinabalu Malaysia Universiti Malaysia Sabah Data Technologies and Application Research Lab Faculty of Computing and Informatics Sabah Kota Kinabalu Malaysia Universiti Kebangsaan Malaysia Centre for Software Technology and Management Faculty of Information Science and Technology Malaysia Telkom University School of Computing Bandung Indonesia Foundation Study and Language Institute University of Reading Malaysia Johor Iskandar Puteri Malaysia

ISBN: (纸本)9798350310689

The Covid-19 pandemic has impacted the world economy, and Malaysia is no exception. Due to the closure of businesses, the rate of unemployment has been recorded at an all-time high. The Malaysian Government through its agencies is assisting citizens through an online platform for incentives and an aid-giving platform. The current architecture of data sharing is using centralized, organization-oriented authentication and is not immutable for audit capability. In addition, the blockchain network is still a proof of concept in the digital government ecosystem. This paper studies the current aid data-sharing ecosystem and analyzes the potential of having a state government consortium blockchain framework that will be used in the Government Network Infrastructure for decentralized, transparent data sharing with audit capability. Several works involving Blockchain adoption based on domain, Blockchain consortium architecture and Government applications using blockchain are being presented. The need for a framework in implementing decentralized data sharing using consortium blockchain architecture for multi-agencies data sharing focusing on Malaysia Government Aid Management is discussed in this paper to provide the opportunity for the research domain. The findings in this paper will be used for future work on the requirement of a proposed government multi-layer consortium blockchain framework for data sharing in the Malaysian Government specifically for the Johore State Government ecosystem. © 2023 IEEE.

关键词： Blockchain

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：