检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Gongbo Li, Yanting Luo, Renqian Hu, Pipi Zhao, Zeru Li, Lingbo Liu, Guoqing Wang, Zun Bi, Ran Gao, Kaiyuan Guo, Liya Xie, Yu Liu, Chang Zhang, Jia Xie, Tian Pinsler, Robert Zeni, Claudio Lu, Ziheng Xia, Yingce Segler, Marwin Riechert, Maik Yuan, Li Chen, Lei Liu, Haiguang Qin, Tao Microsoft Research AI for Science United States School of Electronic and Computer Engineering Peking University China DSA The Hong Kong University of Science and Technology Guangzhou China School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Department of Automation Tsinghua University China School of Computer Science and Technology Huazhong University of Science and Technology China Yau Mathematical Sciences Center Department of Mathematical Sciences Tsinghua University China

Unified generation of sequence and structure for scientific data (e.g., materials, molecules, proteins) is a critical task. Existing approaches primarily rely on either autoregressive sequence models or diffusion models, each offering distinct advantages and facing notable limitations. Autoregressive models, such as GPT, Llama, and Phi-4, have demonstrated remarkable success in natural language generation and have been extended to multimodal tasks (e.g., image, video, and audio) using advanced encoders like VQ-VAE to represent complex modalities as discrete sequences. However, their direct application to scientific domains is challenging due to the high precision requirements and the diverse nature of scientific data. On the other hand, diffusion models excel at generating high-dimensional scientific data, such as protein, molecule, and material structures, with remarkable accuracy. Yet, their inability to effectively model sequences limits their potential as general-purpose multimodal foundation models. To address these challenges, we propose UniGenX, a unified framework that combines autoregressive next-token prediction with conditional diffusion models. This integration leverages the strengths of autoregressive models to ease the training of conditional diffusion models, while diffusion-based generative heads enhance the precision of autoregressive predictions. We validate the effectiveness of UniGenX on material and small molecule generation tasks, achieving a significant leap in state-of-the-art performance for material crystal structure prediction and establishing new state-of-the-art results for small molecule structure prediction, de novo design, and conditional generation. Notably, UniGenX demonstrates significant improvements, especially in handling long sequences for complex structures, showcasing its efficacy as a versatile tool for scientific data generation. © 2025, CC BY.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Modeling Inter-Intra Heterogeneity for Graph Federated Learning 39

Modeling Inter-Intra Heterogeneity for Graph Federated Learn...

引用

39th Annual AAai Conference on Artificial Intelligence, AAai 2025

作者： Yu, Wentao Chen, Shuo Tong, Yongxin Gu, Tianlong Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Center for Advanced Intelligence Project RIKEN Japan State Key Laboratory of Complex & Critical Software Environment Beihang University China Engineering Research Center of Trustworthy AI Ministry of Education Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Heterogeneity is a fundamental and challenging issue in federated learning, especially for the graph data due to the complex relationships among the graph nodes. To deal with the heterogeneity, lots of existing methods perform the weighted federation based on their calculated similarities between pairwise clients (i.e., subgraphs). However, their inter-subgraph similarities estimated with the outputs of local models are less reliable, because the final outputs of local models may not comprehensively represent the real distribution of subgraph data. In addition, they ignore the critical intra-heterogeneity which usually exists within each subgraph itself. To address these issues, we propose a novel Federated learning method by integrally modeling the Inter-Intra Heterogeneity (FedIIH). For the inter-subgraph relationship, we propose a novel hierarchical variational model to infer the whole distribution of subgraph data in a multi-level form, so that we can accurately characterize the inter-subgraph similarities with the global perspective. For the intra-heterogeneity, we disentangle the subgraph into multiple latent factors and partition the model parameters into multiple parts, where each part corresponds to a single latent factor. Our FedIIH not only properly computes the distribution similarities between subgraphs, but also learns disentangled representations that are robust to irrelevant factors within subgraphs, so that it successfully considers the inter- and intra- heterogeneity simultaneously. Extensive experiments on six homophilic and five heterophilic graph datasets in both non-overlapping and overlapping settings demonstrate the effectiveness of our method when compared with nine state-of-the-art methods. Specifically, FedIIH averagely outperforms the second-best method by a large margin of 5.79% on all heterophilic datasets. 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

Prediction Analysis for Diabetic Disease Using Machine Learning Model

Prediction Analysis for Diabetic Disease Using Machine Learn...

引用

Information Technology (OCIT), OITS International Conference on

作者： N. Senthamarai Jafar Ali Ibrahim Syed Masood M. Sathya N. S. Kalyan Chakravarthy Bharati Rathore M Mohamed Kalith Oli Department of Network and Communications SRM Institute of Science and Technology Chennai India Department of IoT School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of IT Nadar Saraswathi College of Engineering and Technology Theni India Center for Data Science AI&ML QIS College of Engineering and Technology Ongole India Faculty of Business and Creative Industries University of South Wales Pontypridd UK School of Bio Sciences and Technology Vellore Institute of Technology Vellore India

ISBN: (数字)9798331510404

ISBN: (纸本)9798331510411

The Diabetes Disease Prediction System is based on predictive modeling, which forecasts the user's disease based on the information that the user inputs to the system, including the number of pregnancies, age, weight, blood pressure, insulin, glucose, and other factors contributing to diabetes. The system evaluates the data supplied by the user as input and outputs the likelihood of the prediction. Nowadays, better production results are key for machine learning activities. research has been conducted on a dataset from the Kaggle data set where single machine learning algorithms have been applied, and recorded results have been compared with results of multialgorithms of machine learning using neural networks. Some major classification algorithms, Random Forest, SVM, and Hybrid model of SVM and Random Forest, have been broadly utilized to anticipate the disease, where different accuracies were obtained. data preprocessing and feature selection were performed before building the models to increase the model's accuracy. Evaluation of the models in the proposed paper is based on the model's accuracy. The hybrid model performed best with 83% accuracy.

关键词： Support vector machines Accuracy Machine learning algorithms Linear regression Predictive models Prediction algorithms Diabetes Classification algorithms Random forests Diseases

来源：评论

学校读者我要写书评

暂无评论

Secure authentication protocol for home area network in smart grid-based smart cities

引用

computers and Electrical engineering 2023年第1期108卷

作者： Badar, Hafiz Muhammad Sanaullah Mahmood, Khalid Akram, Waseem Ghaffar, Zahid Umar, Muhammad Das, Ashok Kumar Department of Computer Science Muhammad Nawaz Sharif University of Agriculture Multan Pakistan Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliu64002 Taiwan Department of Computer Science Lahore Garrison University Lahore Pakistan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Douliu64002 Taiwan Department of Computer Science COMSATS University Islamabad Sahiwal Campus Punjab Pakistan Department of Computer Science Superior University Lahore 54600 Pakistan Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad500 032 India

The Internet of Things (IoT) allows better solutions for managing challenges such as reliability and power quality in a smart grid environment. It also assists in adopting smart grid measures in smart city development. A smart meter in the smart grid environment must securely access services from a service provider via public channels. An adversary can pose several security vulnerabilities as the communication occurs through a public channel. Various researchers recently conducted several research types to determine the most challenging problems with the smart grid. The security features like integrity, authentication, and confidentiality are indispensable requirements of the smart grid environment. On the other hand, different objects like smart meters in the smart grid environment are resource-constrained, posing in designing lightweight security protocols. Hence, we propose a lightweight mutual authentication scheme to offer surveillance to smart meters in smart grid infrastructure. We analyze the suggested protocol against well-known security threats. Finally, we evaluate the performance of the protocol to illustrate its efficiency. © 2023 Elsevier Ltd

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

Design Automation Conference

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao 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 Computer Science and Technology Huazhong University of Science and Technology China Zhejiang Lab Zhejiang-HUST Joint Research Center for Graph Processing China Department of Computer Science University of Warwick United Kingdom

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Revisiting a Simple Mlp Framework for Z-Axis Rotation-Invariant Point Cloud Place Recognition

SSRN

引用

SSRN 2024年

作者： Wu, Junwei Liu, Jiejie Sun, Mingjie Jiang, Chenru Smith, Jeremy Zhang, Quan Department of Electrical Engineering and Electronics University of Liverpool LiverpoolL69 7ZX United Kingdom Department of Computer Science and Technology Soochow University Suzhou China Department of Electrical and Electronic Engineering Xi’an Jiaotong-Liverpool University Suzhou215123 China Data Science Research Center Duke Kunshan University China

The aim of point cloud place recognition is to transform a point cloud into a global descriptor that can be employed in autonomous driving applications to accurately identify the most similar road scene from a large dataset. However, when robots or autonomous vehicles capture point clouds from arbitrary viewpoints, scene rotations often occur, rendering current deep learning-based methods prone to *** evaluate this decline in performance, we introduce a novel metric termed Average Recall@N under arbitrary rotations, abbreviated as ``R-AR@N''. To mitigate this problem, we propose a Geometrical Transformation Module that converts rotation-sensitive coordinates into rotation-invariant representations. Furthermore, we observe that highly complex network designs may not be essential for effective point cloud analysis. In accordance with the simplified architectural approach of PointMLP \cite{pointmlp}, we introduce a Local Feature Transformation module that leverages statistical representations to transform local point features within an appropriate range. This allows the network to capture a variety of geometric structures and produce a robust global *** method is rigorously evaluated on the Oxford outdoor dataset and three proprietary datasets, showing an improvement of at least 2\% over previous methods based on the newly introduced ``R-AR@N'' metric. The code for our approach is available at https://***/jasonwjw/RI-PointMLP. © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Optimization of Small Language Models: A Novel Graph-Theoretical Approach for Efficient Prompt engineering

Fine-Tuning Optimization of Small Language Models: A Novel G...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Venkata Gadiraju Hao-Yu Tsai Hsiao-Chun Wu Manali Singha C.-H. Scott Huang Guannan Liu Shih Yu Chang Yiyan Wu School of Electrical Engineering and Computer Science Louisiana State University Baton Rouge USA Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan Innovation Center for AI Applications Yuan Ze University Chungli Taiwan Institute for Genomic Medicine (IGM) Nationwide Children’s Hospital Columbus USA Department of Applied Data Science San Jose State University San Jose USA Communications Research Centre Ottawa Canada

ISBN: (数字)9798350364262

ISBN: (纸本)9798350364279

In the realm of fine-tuning pre-trained language models in modern prompt engineering, we introduce a novel graph-theoretical approach to address the resource-intensive challenges to the conventional data fine-tuning methods for prompt engineering. Leveraging semantic and contextual prompt relationships, we propose to form a novel prompt graph, which facilitates a new comprehensive representation of prompt similarities. Building upon this new graph structure, our proposed approach can minimize the training time during the fine-tuning process for small language models by identifying and utilizing cliques corresponding to condensed subsets of highly similar prompts. This new strategic reduction in training data can greatly reduce the training time, particularly for resource-constrained applications in practice. Our proposed new approach leads to a significant reduction in the original prompt-graph order and a more focused and streamlined fine-tuning process. This data-reduction strategy demonstrates the potential to enable finetuning language models for prompt engineering with smaller datasets subject to less computational resource. The real run-time analysis for the training process of a small language model GPT2 have been undertaken to show the advantage of our proposed new approach.

关键词： Training Computational modeling Simulation Semantics Training data data models Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

Efficient Resource Allocation in Computing Power Networks Considering Similar Task Merging: A Lyapunov Optimization-Based DRL Approach

引用

IEEE Internet of Things Journal 2025年

作者： Jia, Zhonghai Xue, Junxiao Shi, Lei Li, Jie He, Mengyang Zhejiang Lab Research Center for Space Computing System Hangzhou310000 China Zhengzhou University School of Cyber Science and Engineering Zhengzhou450002 China SongShan Laboratory Zhengzhou450040 China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China Shanghai Key Laboratory of Trusted Data Circulation and Governance Web3 Shanghai China

The cloud-edge-terminal architecture relies on hierarchy for resource allocation but lacks global optimization. The computing power network (CPN) introduces a new distributed computing paradigm, integrating cross-domain, heterogeneous resources for global scheduling. However, most CPN research focuses on task optimization during resource allocation, while neglecting the similarity of random tasks before the allocation stage. Additionally, fragmented CPN resources and complex task demands pose challenges to global load balancing. This paper proposes a deep reinforcement learning framework with task merging and congestion avoidance for on-demand resource allocation. Specifically, a low-complexity similar task merging algorithm reduces redundant resource consumption during task preprocessing. In task offloading, the principal neighborhood aggregated graph neural network captures CPN's intricate features. Lyapunov optimization, integrated into a multi-threaded training framework, minimizes resource backlog congestion. A carefully designed reward function balances multiple objectives, enhancing computing resource utilization efficiency and ensuring system stability. Theoretical analysis shows that with control parameter V, the trade-off between resource utilization efficiency and system stability follows the relationship O(1/V), O(V). Extensive experiments demonstrate a 33.5% improvement in resource utilization efficiency and a 62.7% increase in task offloading success rates with respect to those in state-of-the-art algorithms. The proposed algorithm exhibits robustness and effectiveness, particularly in high-load and real network topologies. © 2014 IEEE.

关键词： Computing power

来源：评论

学校读者我要写书评

暂无评论

Beyond Normal: On the Evaluation of Mutual Information Estimators

arXiv

引用

arXiv 2023年

作者： Czyz, Pawel Grabowski, Frederic Vogt, Julia E. Beerenwinkel, Niko Marx, Alexander Department of Biosystems Science and Engineering ETH Zurich Switzerland ETH AI Center ETH Zurich Switzerland Institute of Fundamental Technological Research Polish Academy of Sciences Poland Department of Computer Science ETH Zurich Switzerland SIB Swiss Institute of Bioinformatics Switzerland

Mutual information is a general statistical dependency measure which has found applications in representation learning, causality, domain generalization and computational biology. However, mutual information estimators are typically evaluated on simple families of probability distributions, namely multivariate normal distribution and selected distributions with one-dimensional random variables. In this paper, we show how to construct a diverse family of distributions with known ground-truth mutual information and propose a language-independent benchmarking platform for mutual information estimators. We discuss the general applicability and limitations of classical and neural estimators in settings involving high dimensions, sparse interactions, long-tailed distributions, and high mutual information. Finally, we provide guidelines for practitioners on how to select appropriate estimator adapted to the difficulty of problem considered and issues one needs to consider when applying an estimator to a new data set. © 2023, CC BY-SA.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Front-running Attacks in Hash-Based Transaction Sharding Blockchains

Front-running Attacks in Hash-Based Transaction Sharding Blo...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Yusen Wang Jiong Lou Zihan Wang Jie Li Department of Computer Science and Engineering Shanghai Jiao Tong University China Blockchain Advanced Research Center Shanghai Jiao Tong University (Wuxi) China Shanghai Key Laboratory of Trusted Data Circulation and Governance and Web3 China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Sharding is one of the prominent solutions to solve the scalability problem of traditional blockchains. By dividing the blockchain network into independent shards, transactions in different shards can be executed in parallel, improving the throughput of the blockchain. However, sharding also brings security issues. In a hash-based transaction sharding system, the output shard of a transaction is determined by the hash value of the transaction. Unfortunately, we show that this hashbased transaction assignment strategy can be easily exploited by attackers to conduct front-running attacks. Attackers can take advantage of the execution differences between different shards and the extra processing time of cross-shard transactions to make the attacker’s transaction executed and committed before the victim’s transaction, thereby obtaining the benefits that originally belonged to the victim. We also propose a flooding front-running attack, which introduces a single-shard flooding attack to enhance the front-running attack. Specifically, injecting a large number of junk transactions into the shard where the victim’s transaction is located can significantly extend the execution time of the victim’s transaction. We demonstrate the feasibility and practical effects of these two attacks through experiments on RapidChain, which show that a single-shard flooding attack can increase the success rate of a front-running attack by 12%. Finally, we discuss two possible mitigation measures and the cost of two proposed attacks.

关键词： Sharding Privacy Costs Prevention and mitigation Scalability Throughput Blockchains Floods Security

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：