检索结果-内蒙古大学图书馆

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Jin, Chunzhen Huang, Yongfeng Wang, Yaqi Cao, Peng Zaïane, Osmar Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong National Frontiers Science Center for Industrial Intelligence and Systems Optimization Shenyang China Amii University of Alberta EdmontonAB Canada

ISBN: (纸本)9781643685489

Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning (SETTP) for effective style transfer in low-resource scenarios. First, SETTP learns source style-level prompts containing fundamental style characteristics from high-resource style transfer. During training, the source style-level prompts are transferred through an attention module to derive a target style-level prompt for beneficial knowledge provision in low-resource style transfer. Additionally, we propose instance-level prompts obtained by clustering the target resources based on the semantic content to reduce semantic bias. We also propose an automated evaluation approach of style similarity based on alignment with human evaluations using ChatGPT-4. Our experiments across three resourceful styles show that SETTP requires only 1/20th of the data volume to achieve performance comparable to state-of-the-art methods. In tasks involving scarce data like writing style and role style, SETTP outperforms previous methods by 16.24%. © 2024 The Authors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decoding six basic emotions from brain functional connectivity patterns

引用

science China(Life sciences) 2023年第4期66卷 835-847页

作者： Chunyu Liu Yingying Wang Xiaoyue Sun Yizhou Wang Fang Fang School of Psychological and Cognitive Sciences and Beijing Key Laboratory of Behavior and Mental Health Peking UniversityBeijing 100871China Department of Psychology and Behavioral Sciences Zhejiang UniversityHangzhou 310028China IDG/McGovern Institute for Brain Research Peking UniversityBeijing 100871China Peking-Tsinghua Center for Life Sciences Peking UniversityBeijing 100871China Center on Frontiers of Computing Studies School of Computer SciencePeking UniversityBeijing 100871China

Although distinctive neural and physiological states are suggested to underlie the six basic emotions,basic emotions are often indistinguishable from functional magnetic resonance imaging(f MRI)voxelwise activation(VA)***,we hypothesize that functional connectivity(FC)patterns across brain regions may contain emotion-representation information beyond VA *** collected whole-brain f MRI data while human participants viewed pictures of faces expressing one of the six basic emotions(i.e.,anger,disgust,fear,happiness,sadness,and surprise)or showing neutral *** obtained FC patterns for each emotion across brain regions over the whole brain and applied multivariate pattern decoding to decode emotions in the FC pattern representation *** results showed that the whole-brain FC patterns successfully classified not only the six basic emotions from neutral expressions but also each basic emotion from other *** emotion-representation network for each basic emotion that spanned beyond the classical brain regions for emotion processing was ***,we demonstrated that within the same brain regions,FC-based decoding consistently performed better than VA-based *** together,our findings revealed that FC patterns contained emotional information and advocated for paying further attention to the contribution of FCs to emotion processing.

关键词： decoding basic emotions functional connectivity voxelwise activation multivariate pattern analysis

来源：评论

学校读者我要写书评

暂无评论

Insightful Mining Equilibria 18th

Insightful Mining Equilibria

引用

18th International Conference on Web and Internet Economics, WINE 2022

作者： Zhang, Mengqian Li, Yuhao Li, Jichen Kong, Chaozhe Deng, Xiaotie Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Columbia University New YorkNY10027 United States Center on Frontiers of Computing Studies School of Computer Science Peking University Beijing100871 China

ISBN: (纸本)9783031228315

The selfish mining attack, arguably the most famous game-theoretic attack in blockchain, indicates that the Bitcoin protocol is not incentive-compatible. Most subsequent works mainly focus on strengthening the selfish mining strategy, thus enabling a single strategic agent more likely to deviate. In sharp contrast, little attention has been paid to the resistant behavior against the selfish mining attack, let alone further equilibrium analysis for miners and mining pools in the blockchain as a multi-agent system. In this paper, first, we propose a novel strategy called insightful mining to counteract the selfish mining attack. By infiltrating an undercover miner into the selfish pool, the insightful pool could acquire the number of its hidden blocks. We prove that, with this extra insight, the utility of the insightful pool is strictly greater than the selfish pool’s when they have the same mining power. Then we investigate the mining game where all pools can choose to be honest or take the insightful mining strategy. We characterize the Nash equilibrium of such a game and derive three corollaries: (a) each mining game has a pure Nash equilibrium;(b) there are at most two insightful pools under some equilibrium no matter how the mining power is distributed;(c) honest mining is a Nash equilibrium if the largest mining pool has a fraction of mining power no more than 1/3. Our work explores, for the first time, the idea of spying in the selfish mining attack, which might shed new light on researchers in the field. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Detecting Informationally-Dense Subsets

Detecting Informationally-Dense Subsets

引用

IEEE (first ITW conference of the year) Information Theory Workshop (ITW)

作者： Chao Zhao Ali Al-Bashabsheh Chung Chan Department of Computer Science City University of Hong Kong. Big Data and Brain Computing (BDBC) center at Beihang University Beijing China

ISBN: (数字)9798350348934

ISBN: (纸本)9798350348941

Identifying locally dense subgraphs aims to pinpoint subgraphs characterized by tight internal connectivity. However, existing methods for identifying dense subgraphs based on density can lead to loose internal connections. This paper addresses this issue by introducing a concept of strength to detect strong subsets. Our approach encompasses the existing work that finds a nested chain of densest k-subgraphs as a special case and reveals subgraphs that have tight internal connections overlooked by existing methods. The strong subsets exhibit a laminar structure and can be computed in polynomial time. In contrast to previous works defining locally densest subgraphs without a natural extension to weighted graphs, our method accommodates both weighted and unweighted, directed and undirected graphs, as well as hypergraphs. Furthermore, it extends to a broader notion of information density, surpassing the scope of weighted graphs.

关键词： Conferences Minimization Polynomials Information theory

来源：评论

学校读者我要写书评

暂无评论

Autoregressive Sequence Modeling for 3D Medical Image Representation 39

Autoregressive Sequence Modeling for 3D Medical Image Repres...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Siwen Wang, Churan Gao, Fei Su, Lixian Zhang, Fandong Wang, Yizhou Yu, Yizhou School of Computing and Data Science The University of Hong Kong Hong Kong Center on Frontiers of Computing Studies School of Computer Science Nat'l Eng. Research Center of Visual Technology Peking University China Deepwise AI Lab China State Key Lab of General Artificial Intelligence Inst. for Artificial Intelligence Peking University China

ISBN: (纸本)157735897X

Three-dimensional (3D) medical images, such as Computed Tomography (CT) and Magnetic Resonance Imaging (MRI), are essential for clinical applications. However, the need for diverse and comprehensive representations is particularly pronounced when considering the variability across different organs, diagnostic tasks, and imaging modalities. How to effectively interpret the intricate contextual information and extract meaningful insights from these images remains an open challenge to the community. While current self-supervised learning methods have shown potential, they often consider an image as a whole thereby overlooking the extensive, complex relationships among local regions from one or multiple images. In this work, we introduce a pioneering method for learning 3D medical image representations through an autoregressive pre-training framework. Our approach sequences various 3D medical images based on spatial, contrast, and semantic correlations, treating them as interconnected visual tokens within a token sequence. By employing an autoregressive sequence modeling task, we predict the next visual token in the sequence, which allows our model to deeply understand and integrate the contextual information inherent in 3D medical images. Additionally, we implement a random startup strategy to avoid overestimating token relationships and to enhance the robustness of learning. The effectiveness of our approach is demonstrated by the superior performance over others on nine downstream tasks in public datasets. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Privacy Leakage in Federated Learning for Smart Grid Short-Term Load Forecasting

Privacy Leakage in Federated Learning for Smart Grid Short-T...

引用

Annual Conference of Industrial Electronics Society

作者： Hussein Aly Abdulaziz Al-Ali Abdulla Al-Ali Qutaibah Malluhi Department of Computer Science and Engineering College of Engineering Qatar University Doha Qatar KINDI Computing Research Center Qatar University Doha Qatar

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

Federated Learning (FL) for household-level Short-Term Load Forecasting (STLF) has emerged as a solution to privacy concerns in smart grids, enabling clients to collaboratively train models without sharing their consumption data with a central server. However, sharing model updates can still introduce privacy risks. A common solution to mitigate this risk is the use of differential privacy during the federation process. However, there is a lack of empirical privacy analysis of these techniques in smart grid scenarios. This paper proposes a property inference attack utilizing a single update per client to evaluate privacy risks in federated learning within smart grid contexts. We assess the privacy risk associated with the standard FedAvg algorithm and a differentially private noise-before-aggregation (NBA) FL scheme. Furthermore, we investigate the trade-off between privacy and utility in the NBA-FL scheme. Our empirical findings reveal significant information leakage with standard FedAvg scheme. An adversary with access to a single model update can identify global data properties of the FedAvg client local dataset with an Area Under the Curve (AUC) of 72%. This privacy leakage can be reduced using NBA-FL, which reduces the AUC to 60%. However, the addition of noise to the model updates results in a utility loss of up to 70% in the model’s predictive power. This significant degradation in model performance outweighs the advantages of the scheme.

关键词： Training Privacy Federated learning Load forecasting Noise Predictive models Data models Smart grids Standards Load modeling

来源：评论

学校读者我要写书评

暂无评论

Associative Forms for Encoding Multivariate Climate Data

Associative Forms for Encoding Multivariate Climate Data

引用

IEEE VIS Arts Program (VISAP)

作者： Francesca Samsel Greg Abram Catherine Bowman Daniel Keefe Texas Advanced Computing Center University of Texas at Austin USA Department of Computer Science University of Minnesota USA

ISBN: (数字)9798350330229

ISBN: (纸本)9798350330236

We are perpetually present in our environment, experiencing it with our senses. Scientific data describes the same environment quantitatively. Our goal is to use scientific and artistic methods to combine these environmental expressions and personal experience through the creation of glyphs visually abstracted from and associated with forms in nature in the representation of climate data. The use of these glyphs removes the distinctions between scientific data and sensory experience, to allow a fuller intuitive association between the two, creating an embodied experience and increasing awareness of the climate effects and changes all around us.

关键词： Earth Art Antarctic Ocean Encoding Biological information theory Meteorology

来源：评论

学校读者我要写书评

暂无评论

Hinge-Wasserstein: Estimating Multimodal Aleatoric Uncertainty in Regression Tasks

arXiv

引用

arXiv 2023年

作者： Xiong, Ziliang Jonnarth, Arvi Eldesokey, Abdelrahman Johnander, Joakim Wandt, Bastian Forssén, Per-Erik Computer Vision Laboratory Department of Electrical Engineering LiU Sweden Visual Computing Center KAUST Saudi Arabia Husqvarna Group Huskvarna Sweden Zenseact Sweden

computer vision systems that are deployed in safety-critical applications need to quantify their output uncertainty. We study regression from images to parameter values and here it is common to detect uncertainty by predicting probability distributions. In this context, we investigate the regression-by-classification paradigm which can represent multimodal distributions, without a prior assumption on the number of modes. Through experiments on a specifically designed synthetic dataset, we demonstrate that traditional loss functions lead to poor probability distribution estimates and severe overconfidence, in the absence of full ground truth distributions. In order to alleviate these issues, we propose hinge-Wasserstein – a simple improvement of the Wasserstein loss that reduces the penalty for weak secondary modes during training. This enables prediction of complex distributions with multiple modes, and allows training on datasets where full ground truth distributions are not available. In extensive experiments, we show that the proposed loss leads to substantially better uncertainty estimation on two challenging computer vision tasks: horizon line detection and stereo disparity estimation. The code is available at:https://***/XZLeo/ hinge-Wasserstein Copyright © 2023, The Authors. All rights reserved.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Battery-Induced Load Hiding and Its Utility Consequences

Battery-Induced Load Hiding and Its Utility Consequences

引用

Workshop on Smart Grid and Renewable Energy (SGRE)

作者： Hussein Aly Emran Altamimi Abdulaziz Al-Ali Abdulla Al-Ali Qutaibah Malluhi Department of Computer Science and Engineering College of Engineering Qatar University Doha Qatar Kindi Center for Computing Research Qatar University Doha Qatar

The introduction of smart grids allows utility providers to collect detailed data about consumers, which can be utilized to enhance grid efficiency and reliability. However, this data collection also raises privacy concerns. To protect user privacy, some studies suggest using battery-based load hiding. Nevertheless, the impact of widespread adoption of this approach on utility providers remain unclear. Our paper seeks to evaluate the effects of battery-based load hiding on two critical operations: user profiling and anomaly detection. Our findings reveal that the inclusion of battery users in datasets can diminish the quality of conclusions drawn from these data. This can result in a decrease in the Area Under the Curve (AUC) by more than 10% when attempting to profile users within single-occupant and multiple-occupant households. Furthermore, our experiments demonstrate that battery-based load hiding not only conceals information about users employing the batteries but can also lead to an increased rate of false positives for other non-battery users (from 0.15 to 0.37) within the system. To mitigate these adverse effects, our study assessed various mitigation strategies. In the context of user profiling, our experiment demonstrated that identifying and removing battery users from the analytical dataset using unsupervised detection methods can effectively lessen the impact of battery users. For anomaly detection, our experiment revealed that creating separate classification models for battery and non-battery users can significantly reduce the adverse influence of battery users on the detection performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

M2-Fi: Multi-person Respiration Monitoring via Handheld WiFi Devices

M2-Fi: Multi-person Respiration Monitoring via Handheld WiFi...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Jingyang Hu Hongbo Jiang Tianyue Zheng Jingzhi Hu Hongbo Wang Hangcheng Cao Zhe Chen Jun Luo College of Computer Science and Electronic Engineering Hunan University China School of Computer Science and Engineering Nanyang Technological University (NTU) Singapore Department of Computer Science City University of Hong Kong China Intelligent Networking and Computing Research Center and School of Computer Science Fudan University China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Wi-Fi signals are commonly used for conventional communication, yet they can also realize low-cost and non-invasive human sensing. However, Wi-Fi sensing in Multi-person scenarios is still a challenging problem. In this paper, we propose M 2 -Fi to achieve multi-person respiration monitoring using a handheld device. M 2 -Fi leverages Wi-Fi BFI (beamforming feedback information) performs respiration monitoring. As a compressed version of the uplink CSI (channel state information), BFI transmission is unencrypted, easily obtained using frame capture, and does not require specific firmware to obtain. M 2 -Fi is based on an interesting experiment phenomenon that when a Wi-Fi device is very close to a subject, near-field channel changes caused by the subject significantly cancel out changes from other subjects. We employed VMD (Variational Mode Decomposition) to eliminate the interference caused by hand movement in the BFI time series. Subsequently, we devised a deep learning architecture based on GAN (Generative Adversarial Networks) to recover fine-grained respiration waveforms from the respiration patterns extracted from the BFI time series. Our experiments on collected 50-hour data from 8 subjects show that M 2 -Fi can accurately recover the respiration waveforms of multiple persons with handheld devices.

关键词： Performance evaluation Time series analysis Interference Generative adversarial networks Hardware Sensors Uplink

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：