检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Du, Jing Ye, Zesheng Guo, Bin Yu, Zhiwen Yao, Lina School of Computer Science and Engineering The University of New South Wales Australia School of Computer Science Northwestern Polytechnical University China CSIRO's Data 61 The University of New South Wales Australia

Learning accurate cross-domain preference mappings in the absence of overlapped users/items has presented a persistent challenge in Non-overlapping Cross-domain Recommendation (NOCDR). Despite the efforts made in previous studies to address NOCDR, several limitations still exist. Specifically, 1) while some approaches substitute overlapping users/items with overlapping behaviors, they cannot handle NOCDR scenarios where such auxiliary information is unavailable;2) often, cross-domain preference mapping is modeled by learning deterministic explicit representation matchings between sampled users in two domains. However, this can be biased due to individual preferences and thus fails to incorporate preference continuity and universality of the general population. In light of this, we assume that despite the scattered nature of user behaviors, there exists a consistent latent preference distribution shared among common people. Modeling such distributions further allows us to capture the continuity in user behaviors within each domain and discover preference invariance across domains. To this end, we propose a Distributional domain-invariant Preference Matching method for non-overlapping Cross-Domain Recommendation (DPMCDR). For each domain, we hierarchically approximate a posterior of domain-level preference distribution with empirical evidence derived from user-item interactions. Next, we aim to build distributional implicit matchings between the domain-level preferences of two domains. This process involves mapping them to a shared latent space and seeking a consensus on domain-invariant preference by minimizing the distance between their distributional representations therein. In this way, we can identify the alignment of two non-overlapping domains if they exhibit similar patterns of domain-invariant preference. Experiments on real-world datasets demonstrate that DPMCDR outperforms the state-of-the-art approaches with a range of evaluation metrics. © 2023, CC BY-NC-

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Advancing Brain-computer Interaction: EEG-based Eye Movement Recognition with AI 7

Advancing Brain-Computer Interaction: EEG-based Eye Movement...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Saidala, Ravi Kumar Ramnath, M. Komala, C.R. Vidhya, N.G. Taqui, Syed Noeman Rajendiran, M. Alliance University Department of Computer Science And Engineering Karnataka Bangalore560076 India Ramco Institute of Technology Department of Artificial Intelligence And Data Science Tamil Nadu Rajapalayam626117 India Hkbk College of Engineering Department of Information Science And Engineering Bengaluru560 045 India St. Joseph's Institute of Technology Omr Department of Information Technology Tamil Nadu Chennai600119 India Saveetha Institute of Medical And Technical Sciences Saveetha School of Engineering Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India Panimalar Engineering College Department of Computer Science And Engineering Tamil Nadu Chennai600123 India

ISBN: (纸本)9798350359299

The integration of Electroencephalography (EEG) and Brain-computer Interface (BCI) technologies is causing an evolution in healthcare, accessibility, and neuroscience. This multidisciplinary method offers a non-invasive means to communicate and control through intentional eye movements, which is particularly promising for patients suffering from neurological illnesses. In this study, eye movements are identified using EEG data from the EPOC Flex wireless EEG brain device. Using advanced Deep Learning models such as the Deep Belief Network (DBN) and the Deep Residual Network (Deep ResNet), and attempted to distinguish four distinct eye movements: open, close, right, and left. Some of the primary metrics utilized for assessing these models were accuracy, precision, recall, and F1 score. The Deep ResNet model gives better results with an accuracy of 96.25%, recall of 95.85%, precision of 96.66%, and an F1 score of 96.24%. The findings suggest that BCI frameworks can leverage EEG-based eye movement detection to improve rehabilitation procedures and make computers and devices easier to operate. This study's findings open a path for future research into neurotechnological applications and human-computer interaction. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning

StyleAdv: Meta Style Adversarial Training for Cross-Domain F...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yuqian Fu Yu Xie Yanwei Fu Yu-Gang Jiang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Purple Mountain Laboratories Nanjing China School of Data Science Fudan University

Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles few-shot learning across different domains. It aims at transferring prior knowledge learned on the source dataset to novel target datasets. The CD-FSL task is especially challenged by the huge domain gap between different datasets. Critically, such a domain gap actually comes from the changes of visual styles, and wave-SAN [10] empirically shows that spanning the style distribution of the source data helps alleviate this issue. However, wave-SAN simply swaps styles of two images. Such a vanilla operation makes the generated styles “real” and “easy”, which still fall into the original set of the source styles. Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL. Particularly, our style attack method synthesizes both “virtual” and “hard” adversarial styles for model training. This is achieved by perturbing the original style with the signed style gradients. By continually attacking styles and forcing the model to recognize these challenging adversarial styles, our model is gradually robust to the visual styles, thus boosting the generalization ability for novel target datasets. Besides the typical CNN-based backbone, we also employ our StyleAdv method on large-scale pre-trained vision transformer. Extensive experiments conducted on eight various target datasets show the effectiveness of our method. Whether built upon ResNet or ViT, we achieve the new state of the art for CD-FSL. Code is available at https://***/lovelyqian/StyleAdv-CDFSL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anytime Acceleration of Gradient Descent

arXiv

引用

arXiv 2024年

作者： Zhang, Zihan Lee, Jason D. Du, Simon S. Chen, Yuxin Paul G. Allen School of Computer Science and Engineering University of Washington United States Department of Electrical and Computer Engineering Princeton University United States Department of Statistics and Data Science University of Pennsylvania United States

This work investigates stepsize-based acceleration of gradient descent with anytime convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsize schedule that allows gra- dient descent to achieve convergence guarantees of O(T− 2 log2 ρ/ 1+log2 ρ) ≈ O(T−1.119) for any stopping time T, where ρ = √2 + 1 is the silver ratio and the stepsize schedule is predetermined without prior knowledge of the stopping time. This result provides an affirmative answer to a COLT open problem (Kornowski and Shamir, 2024) regarding whether stepsize-based acceleration can yield anytime convergence rates of o(T−1). We further extend our theory to yield anytime convergence guarantees of exp(−Ω(T/κ0.893)) for smooth and strongly convex optimization, with κ being the condition number. Copyright © 2024, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A New Federated Learning Framework Against Gradient Inversion Attacks 39

A New Federated Learning Framework Against Gradient Inversio...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Guo, Pengxin Zeng, Shuang Chen, Wenhao Zhang, Xiaodan Ren, Weihong Zhou, Yuyin Qu, Liangqiong School of Computing and Data Science The University of Hong Kong Hong Kong Department of Mathematics The University of Hong Kong Hong Kong College of Computer Science Beijing University of Technology China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering UC Santa Cruz United States

ISBN: (纸本)157735897X

Federated Learning (FL) aims to protect data privacy by enabling clients to collectively train machine learning models without sharing their raw data. However, recent studies demonstrate that information exchanged during FL is subject to Gradient Inversion Attacks (GIA) and, consequently, a variety of privacy-preserving methods have been integrated into FL to thwart such attacks, such as Secure Multi-party Computing (SMC), Homomorphic Encryption (HE), and Differential Privacy (DP). Despite their ability to protect data privacy, these approaches inherently involve substantial privacy-utility trade-offs. By revisiting the key to privacy exposure in FL under GIA, which lies in the frequent sharing of model gradients that contain private data, we take a new perspective by designing a novel privacy preserve FL framework that effectively "breaks the direct connection" between the shared parameters and the local private data to defend against GIA. Specifically, we propose a Hypernetwork Federated Learning (HyperFL) framework that utilizes hypernetworks to generate the parameters of the local model and only the hypernetwork parameters are uploaded to the server for aggregation. Theoretical analyses demonstrate the convergence rate of the proposed HyperFL, while extensive experimental results show the privacy-preserving capability and comparable performance of HyperFL. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Assessing the Feasibility of Incorporating AI for Efficient data Access Strategies

Assessing the Feasibility of Incorporating AI for Efficient ...

引用

2023 IEEE International Conference on Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario, ICPSITIAGS 2023

作者： Yadav, Dhyan Geetha, G. Elackiya, R. Kumar, Santosh D. Sharma, Ritu Jain, Romil Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Karnataka Bangalore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350329773

The use of AI in statistics gets entry to techniques has recently emerged as a critical topic in the discipline of the information era. AI and gadgets gaining knowledge of strategies can enhance the performance and accuracy of facts to get entry to strategies. Also, they can offer extra blessings, including advanced scalability, privacy, and protection. This paper examines the feasibility of incorporating AI for efficient information entry techniques. An in-depth review of present studies inside the place of AI for statistics gets entry is supplied, highlighting the challenges and possibilities related to its use. The paper also examines the practical factors of incorporating AI for information get entry to techniques and assesses the price, scalability, and complexity of such procedures. We concluded that incorporating AI for records access techniques is viable and might benefit information customers significantly. However, similar studies are wanted to decide the most incredible layout and implementation of such techniques. © 2023 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Hybrid System with Modified Cuckoo Search to Design Airfoil

Hybrid System with Modified Cuckoo Search to Design Airfoil

引用

data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： K. Thinakaran M. Anand T.Rajesh Kumar Saira Banu Atham K.M. Subramanian Department of Computer Science Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Chennai Saveetha School of Engineering Saveetha Institute of Medical and Technical Science Department of Computer Science and Engineering School of CSE & IS Presidency University Bangaluru Department of Computer Science Engineering Shadan College of Engineering and Technology Hyderabad

The proposed models can design the airfoil by Cuckoo search with Levenberg-Marquardt. The Neural Network framework has impediments due to over-fitting. This paper proposed a modified cuckoo search. here the aerodynamic coefficient as an input to produce output the airfoil coordinates. The generated airfoil is compared to know its performance metrics. The Cuckoo search with the Feedforward Neural Network model yields the lowest prediction error.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Link/Switch Fault-Tolerant Hamiltonian Path Embedding in BCube Networks for Deadlock-Free Routing

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Lin, Wanling Li, Xiao-Yan Chang, Jou-Ming Xiang, Dong Jia, Xiaohua Fuzhou University College of Computer and Data Science Fuzhou350108 China National Taipei University of Business Institute of Information and Decision Sciences Taipei10051 Taiwan Tsinghua University School of Software Beijing100084 China City University of Hong Kong Department of Computer Science Hong Kong

BCube stands as a renowned server-centric data center network (DCN), boasting numerous advantages, such as low diameter, high aggregate throughput, and abundant parallel paths. As DCNs expand rapidly, followed by the daily increasing likelihood of failures, fault tolerance has become an important issue in DCNs. Hamiltonian paths constitute a pivotal network topology for parallel and distributed computing, suitable for designing deadlock-free routing algorithms, fault-tolerant routing algorithms, and congestion avoidance. The partitioned edge fault (PEF) model is a recently proposed fault model that exploits the properties of networks to achieve fault tolerance with an exponential scale. In this paper, we explore the existence of Hamiltonian paths in BCube under the PEF model. Since one switch failure will result in multiple faulty links, we also extend the conclusions related to Hamiltonian paths to analyze the fault tolerance of BCube under the PEF model when switch failures occur. Moreover, we provide algorithms to embed a Hamiltonian path between arbitrary two distinct servers into BCube under the PEF model. Experimental analysis and comparisons demonstrate that our approach exhibits exponential enhancements over the other known results, and BCube DCNs possess remarkable fault tolerance in response to both link and switch failures under the PEF model. As a by-product, we obtain a deadlock-free routing based on the constructed Hamiltonian path and assess the routing performance compared to the benchmark routing algorithms. © 2004-2012 IEEE.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model

arXiv

引用

arXiv 2023年

作者： Cao, Chenjie Cai, Yunuo Dong, Qiaole Wang, Yikai Fu, Yanwei School of Data Science Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China Alibaba Group China

This paper introduces LeftRefill, an innovative approach to efficiently harness large Text-to-Image (T2I) diffusion models for reference-guided image synthesis. As the name implies, LeftRefill horizontally stitches reference and target views together as a whole input. The reference image occupies the left side, while the target canvas is positioned on the right. Then, LeftRefill paints the right-side target canvas based on the left-side reference and specific task instructions. Such a task formulation shares some similarities with contextual inpainting, akin to the actions of a human painter. This novel formulation efficiently learns both structural and textured correspondence between reference and target without other image encoders or adapters. We inject task and view information through cross-attention modules in T2I models, and further exhibit multi-view reference ability via the re-arranged self-attention modules. These enable LeftRefill to perform consistent generation as a generalized model without requiring test-time fine-tuning or model modifications. Thus, LeftRefill can be seen as a simple yet unified framework to address reference-guided synthesis. As an exemplar, we leverage LeftRefill to address two different challenges: reference-guided inpainting and novel view synthesis, based on the pre-trained StableDiffusion. Codes&models are released at https://***/ewrfcas/LeftRefill. © 2023, CC BY-NC-SA.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Apache Kafka on Big data Event Streaming for Enhanced data Flows 8

Apache Kafka on Big Data Event Streaming for Enhanced Data F...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Padmanaban, K. Babu, T.R. Ganesh Karthika, K. Pattanaik, Balachandra Dhanabhavithra, K. Srinivasan, C. Department of Electronics and Communication Engineering Tamil Nadu Namakkal India Kcg College of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Wollega University Department of Electrical and Computer Engineering Nekemte Ethiopia Agni College of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Chennai India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350376425

Apache Kafka's distributed architecture and message queuing capabilities offer significant improvements in real-time and batch data processing efficiency and reliability. This research aims to optimize Kafka setups, data partitioning, and Kafka Connect integration to create a robust and scalable data streaming infrastructure. The study focuses on enhancing data input, processing, and dissemination across systems and applications. By optimizing Kafka configurations and leveraging its capabilities, the research seeks to achieve significant improvements in data processing speed, real-time analytics, and scalable data pipelines. The evaluation of Kafka Event Stream Throughput Over Time and Latency Distribution Across Brokers demonstrates the system's performance and efficiency. The results indicate a throughput of 750-1340 events per hour and a latency distribution of 6-15 milliseconds. Additionally, Consumer Lag Over Time analysis reveals consistent performance with values ranging from 70-140. This research contributes to the advancement of big data processing by demonstrating the effectiveness of Apache Kafka in creating a robust and efficient data streaming infrastructure. The findings provide valuable insights for organizations seeking to optimize their data pipelines and leverage the power of real-time analytics. © 2024 IEEE.

关键词： data streams

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：