检索结果-内蒙古大学图书馆

8th International Conference on computer and Communication Systems, ICCCS 2023

作者： Xia, Yingying Lu, Bo Ji, Jianmin School of Data Science University of Science and Technology of China Hefei China School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9781665456128

Incremental learning has received significant attention, but the problem of catastrophic forgetting remains a major challenge for existing approaches. This issue hinders models from accumulating knowledge over long stretches. To address this problem, we propose a new approach called Attention Loss function based on Row-Sparsity (ALRS) that mines significant patches by simultaneously learning patch weights and logits (class vectors) using the same parameters. We integrate the attention mechanism with the novel loss function to avoid catastrophic forgetting. This innovative approach enables the model to conflate the newly introduced classes with the existing ones, without the need to store any data or models from the previous steps' base classes. To assess its efficacy, we incorporate ALRS into the distillation loss for validation and conduct a thorough evaluation of the approach's performance on three datasets: CIFAR-100, Caltech-101, and CUBS-200-2011. Compared to LWM, which also does not store data, our method achieves an average improvement of more than 8 percentage points with an absolute advantage on CIFAR-100. Additionally, on Caltech-101 and CUBS-200-2011, our new approach provides comparable accuracy to baseline. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Functional Connectivity Disruptions in Alzheimer’s Disease: A Maximum Flow Perspective 12th

Functional Connectivity Disruptions in Alzheimer’s Disease...

引用

12th International Conference on Computational Advances in Bio and Medical sciences, ICCABS 2023

作者： Stubby, Emma T. Razavi, Seyed Majid Khanmohammadi, Sina School of Computer Science University of Oklahoma Norman73019 United States Data Science and Analytics Institute University of Oklahoma Norman73019 United States

ISBN: (纸本)9783031827679

Alzheimer’s disease is a neurological disorder characterized by functional and structural atrophy, leading to symptoms like memory loss and cognitive decline. This study seeks to analyze the disruptions of functional connectivity pathways within the brain caused by Alzheimer’s disease from the maximum flow perspective. More specifically, we computed the maximum flow pathways within the functional brain networks, and compared it between healthy controls and Alzheimer’s patients. Our results suggest that the Alzheimer’s patients utilize pathways related to the default mode network (DMN) more frequently and display significant alterations in the usage of paths connected to the striate cortex (SC). The increased usage of DMN pathways might point to a compensation mechanism that facilitates interregional communications in Alzheimer’s patients. Understanding the nature of such a compensation mechanism could help develop new treatment options for Alzheimer’s patients. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Privet: A Privacy-Preserving Vertical Federated Learning Service for Gradient Boosted Decision Tables

引用

IEEE Transactions on Services Computing 2023年第5期16卷 3604-3620页

作者： Zheng, Yifeng Xu, Shuangqing Wang, Songlei Gao, Yansong Hua, Zhongyun Harbin Institute of Technology School of Computer Science and Technology Guangdong Shenzhen518055 China Csiro Data61 SydneyNSW2720 Australia

Vertical federated learning (VFL) has recently emerged as an appealing distributed paradigm empowering multi-party collaboration for training high-quality models over vertically partitioned datasets. Gradient boosting has been popularly adopted in VFL, which builds an ensemble of weak learners (typically decision trees) to achieve promising prediction performance. Recently there have been growing interests in using decision table as an intriguing alternative weak learner in gradient boosting, due to its simpler structure, good interpretability, and promising performance. In the literature, there have been works on privacy-preserving VFL for gradient boosted decision trees, but no prior work has been devoted to the emerging case of decision tables. Training and inference on decision tables are different from that in the case of generic decision trees, not to mention gradient boosting with decision tables in VFL. In light of this, we design, implement, and evaluate Privet, the first system framework enabling privacy-preserving VFL service for gradient boosted decision tables. Privet delicately builds on lightweight cryptography and allows an arbitrary number of participants holding vertically partitioned datasets to securely train gradient boosted decision tables. Extensive experiments over several real-world datasets and synthetic datasets demonstrate that Privet achieves promising performance, with utility comparable to plaintext centralized learning. © 2008-2012 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Group Buying Recommendation Model Based on Multi-task Learning 39

Group Buying Recommendation Model Based on Multi-task Learni...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Zhai, Shuoyao Liu, Baichuan Yang, Deqing Xiao, Yanghua Fudan University School of Data Science Shanghai200433 China Fudan University School of Computer Science Shanghai200433 China Shanghai Key Laboratory of Data Science Shanghai200433 China

ISBN: (纸本)9798350322279

In recent years, group buying has become one popular kind of online shopping activities, thanks to its larger sales and lower unit price. Unfortunately, seldom research focuses on the recommendations specifically for group buying by now. Although some recommendation models have been proposed for group recommendation, they can not be directly used to achieve the real-world group buying recommendation, due to the essential difference between group recommendation and group buying recommendation. In this paper, we first formalize the task of group buying recommendation into two sub-tasks. Then, based on our insights into the correlations and interactions between the two sub-tasks, we propose a novel recommendation model for group buying, namely MGBR, which is built mainly with a multi-task learning module. To improve recommendation performance further, we devise some collaborative expert networks and adjusted gates in the multi-task learning module, to promote the information interaction between the two sub-tasks. Furthermore, we propose two auxiliary losses corresponding to the two sub-tasks, to refine the representation learning in our model. Our extensive experiments not only demonstrate that the augmented representations learned in our model result in better performance than previous recommendation models, but also justify the impacts of the specially designed components in our model. To reproduce our model's recommendation results conveniently, we have provided our model's source code and dataset on https://***/DeqingYang/MGBR. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Accelerating Blockchain-Enabled Federated Learning with Clustered Clients

引用

IEEE Transactions on Big data 2024年 1-14页

作者： Cui, Laizhong Li, Yinghao Zhou, Yipeng Qu, Youyang Liu, Jiangchuan College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computing FSE Macquarie University Macquare Park NSW Australia Data61 CSIRO VIC Australia School of Computing Science Simon Fraser University Burnaby BC Canada

With the rapid development of big data, Federated learning (FL) has found numerous applications, enabling machine learning (ML) on edge devices while preserving privacy. However, FL still faces crucial challenges, such as single point of failure and poisoning attacks, which motivate the integration of blockchain-enabled FL (BeFL). Beyond that, the efficiency issue still limits the further application of BeFL. To address these issues, we propose a novel decentralized framework: Accelerating Blockchain-Enabled Federated Learning with Clustered Clients (ABFLCC), who utilize actual training time for clustering clients to achieve hierarchical FL and solve the single point of failure problem through blockchain. Additionally, the framework clusters edge devices considering their actual training times, which allows for synchronous FL within clusters and asynchronous FL across clusters simultaneously. This approach guarantees that devices with a similar training time have a consistent global model version, improving the stability of the converging process, while the asynchronous learning between clusters enhances the efficiency of convergence. The proposed framework is evaluated through simulations on three real-world public datasets, demonstrating a training efficiency improvement of 30% to 70% in terms of convergence time compared to existing BeFL systems. IEEE

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Alignment Work for Urban Accessibility: A Study of How Wheelchair Users Travel in Urban Spaces

引用

Proceedings of the ACM on Human-computer Interaction 2022年第CSCW2期6卷 1–22页

作者： Wu, Yiying Ding, Xianghua Dai, Xuelan Zhang, Peng Lu, Tun Gu, Ning School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China School of Computing Science University of Glasgow Glasgow United Kingdom

Mobility is the key for people with disabilities to have full participation in life. To support their mobility, previous work primarily focused on accessibility as an attribute of the external environment to be evaluated, labeled, visualized, and improved. Relatively less work has looked at how people with disabilities go out and move around in practice and work to achieve mobility. This paper presents a qualitative study of 14 wheelchair users' travel practices in everyday life in China, highlighting urban accessibility as alignment work-the use of an awareness of the conditions along the journey to continuously align and re-Align various resources to ensure accessibility and mobility across contexts and moments. By highlighting alignment work, we present another side of the story of urban accessibility, and broaden design considerations to support mobility for wheelchair users. © 2022 ACM.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Beyond Labels and Topics: Discovering Causal Relationships in Neural Topic Modeling 24

Beyond Labels and Topics: Discovering Causal Relationships i...

引用

33rd ACM Web Conference, WWW 2024

作者： Tang, Yi-Kun Huang, Heyan Shi, Xuewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Data Science and Artificial Intelligence Dongbei University of Finance and Economics Liaoning Dalian China

ISBN: (纸本)9798400701719

Topic models that can take advantage of labels are broadly used in identifying interpretable topics from textual data. However, existing topic models tend to merely view labels as names of topic clusters or as categories of texts, thereby neglecting the potential causal relationships between supervised information and latent topics, as well as within these elements themselves. In this paper, we focus on uncovering possible causal relationships both between and within the supervised information and latent topics to better understand the mechanisms behind the emergence of the topics and the labels. To this end, we propose Causal Relationship-Aware Neural Topic Model (CRNTM), a novel neural topic model that can automatically uncover interpretable causal relationships between and within supervised information and latent topics, while concurrently discovering high-quality topics. In CRNTM, both supervised information and latent topics are treated as nodes, with the causal relationships represented as directed edges in a Directed Acyclic Graph (DAG). A Structural Causal Model (SCM) is employed to model the DAG. Experiments are conducted on three public corpora with different types of labels. Experimental results show that the discovered causal relationships are both reliable and interpretable, and the learned topics are of high quality comparing with eight start-of-the-art topic model baselines. © 2024 ACM.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

STIOS: A Novel Self-supervised Diffusion Model for Trajectory Imputation in Open Environment Scenarios 17

STIOS: A Novel Self-supervised Diffusion Model for Trajector...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart data, Smartdata 2024

作者： Hu, Zhijing Yan, Hao Zheng, Yuhao He, Hua Chen, Chao Fan, Changjun Huang, Kuihua National University of Defense Technology Laboratory for Big Data Data and Decision Changsha China Central South University School of Computer Science and Engineering Changsha China

ISBN: (纸本)9798350351637

With the growth of location-based services, the accumulation of large amounts of trajectory data comes with the challenge of missing data. Existing trajectory imputation methods rely on deterministic models that cannot take into account open environments scenarios without auxiliary information. This may lead to poor performance in learning the long-term dependencies of trajectories. In this paper, we propose a novel Self-supervised diffusion model for Trajectory Imputation in Open environment Scenarios (STIOS), which combines a deterministic model and a conditional diffusion model. In addition, we propose a self-supervised training method inspired by masked language modelling that divides the data into conditional information and estimation targets. Extensive experiments on two real datasets demonstrate the superiority of STIOS for trajectory imputation. © 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

Few-Shot and Transfer Learning with Manifold Distributed datasets 21st

Few-Shot and Transfer Learning with Manifold Distributed D...

引用

21st Australasian Conference on data science and Machine Learning, AusDM 2023

作者： Qayyumi, Sayed Waleed Park, Laurence A. F. Obst, Oliver Centre for Research in Mathematics and Data Science School of Computer Data and Mathematical Sciences Western Sydney University Locked Bag 1797 PenrithNSW2751 Australia

ISBN: (纸本)9789819986958

A manifold distributed dataset with limited labels makes it difficult to train a high-mean accuracy classifier. Transfer learning is beneficial in such circumstances. For transfer learning to succeed, the target and base datasets should have a similar manifold structure. A novel method is presented in this paper for determining the similarity between two manifold structures. To determine whether target and base datasets have similar manifolds and are suitable for transfer learning, this method can be used. A novel few-shot algorithm is then presented that uses transfer learning to classify manifold distributed datasets with a limited number of labels. Using the base and target datasets, the manifold structure and its relevant label distribution are learned. Using this information in combination with the few labels and unlabeled data from the target dataset, we can develop a classifier with high mean accuracy. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Few-shot learning manifold distributed datasets measuring similarity Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Face Forgery Detection Based on Fine-Grained Clues and Noise Inconsistency

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 144-158页

作者： Zhang, Dengyong He, Ruiyi Liao, Xin Li, Feng Chen, Jiaxin Yang, Gaobo Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation the School of Computer and Communication Engineering Changsha410114 China Hunan University Changsha410082 China

Deepfake detection has gained increasing research attention in media forensics, and a variety of works have been produced. However, subtle artifacts might be eliminated by compression, and the convolutional neural networks (CNNs)-based detectors are invalidated for fake face images with compression. In this work, we propose a two-stream network for deepfake detection. We observed that high-frequency noise features and spatial features are inherently complementary to each other. Thus, both spatial features and high-frequency noise features are exploited for face forgery detection. Specifically, we design a double-frequency transformer module (DFTM) to guide the learning of spatial features from local artifact regions. To effectively fuse spatial features and high-frequency noise features, a dual-domain attention fusion module (DDAFM) is designed. We also introduce a local relationship constraint loss, which requires only image-level labels, for model training. We evaluate the proposed approach on five large-scale benchmark datasets, and extensive experimental results demonstrate the proposed approach outperforms most SOTA works. © 2024 IEEE.

关键词： Frequency domain analysis

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：