检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Jun-Peng Jiang Han-Jia Ye Leye Wang Yang Yang Yuan Jiang De-Chuan Zhan School of Artificial Intelligence and National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Key Lab of High Confidence Software Technologies (Peking University) Ministry of Education & School of Computer Science Peking University Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Transferring knowledge across diverse data modalities is receiving increasing attention in machine learning. This paper tackles the task of leveraging expert-derived, yet expensive, tabular data to enhance image-based predictions when tabular data is unavailable during inference. The primary challenges stem from the inherent complexity of accurately mapping diverse tabular data to visual contexts, coupled with the necessity to devise distinct strategies for numerical and categorical tabular attributes. We propose CHannel tAbulaR alignment with optiMal tranSport (CHARMS), which establishes an alignment between image channels and tabular attributes, enabling selective knowledge transfer that is pertinent to visual features. Specifically, CHARMS measures similarity distributions across modalities to effectively differentiate and transfer relevant tabular features, with a focus on morphological characteristics, enhancing the capabilities of visual classifiers. By maximizing the mutual information between image channels and tabular features, knowledge from both numerical and categorical tabular attributes are extracted. Experimental results demonstrate that CHARMS not only enhances the performance of image classifiers but also improves their interpretability by effectively utilizing tabular knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Modeling for Improving Prediction of Toxicity 23

Uncertainty-Aware Modeling for Improving Prediction of Toxic...

引用

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Zhou, Xinlei Wang, Xizhao Zhou, Xinpeng Tu, Siwu Ranwang School of Mathematical Sciences Shenzhen University Shenzhen518060 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China College of Electronic Information Guangxi Minzu University 530000 China Jiangxi Drug Inspection Center Nanchang330001 China

ISBN: (纸本)9798331528041

Accurately predicting molecular toxicity is challenging in drug discovery and chemical safety assessment. Except for the representation of molecular structure, the inherent class imbalance and uncertainty often complicate the task. In this work, we present UnBGMT (Uncertainty-Aware Balanced Graph Multi-set Transformer), which integrates uncertainty modeling into the Graph Multiset Transformer (GMT) framework to improve the reliability and accuracy of molecular toxicity predictions. Our method employs Monte Carlo dropout (MC dropout) to evaluate uncertainty, which is then used to guide an adaptive loss function that adjusts weights in training. This approach guides the model to focus on the minority and samples with middle-level uncer-tainty, mitigating issues related to class imbalance and improving model stability. We conducted sufficient experiments on the Tox21 dataset, demonstrating the superiority of UnBGMT by comparing performance with baseline models and conducting ablation studies. Our results highlight the benefits of incorporating uncertainty in toxicity prediction, which provides a deeper insight into the im-pact of uncertainty on model performance. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Simultaneous Layout Decomposition and Mask Optimization

Deep Learning-Driven Simultaneous Layout Decomposition and M...

引用

作者： Zhong, Wei Hu, Shuxiang Ma, Yuzhe Yang, Haoyu Ma, Xiuyuan Yu, Bei DUTRU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian116024 China

Combining multiple patterning lithography (MPL) and optical proximity correction (OPC) pushes the limit of 193-nm wavelength lithography to go further. Considering that layout decomposition may generate plenty of solutions with diverse printabilities, relying on conventional mask optimization (MO) process to select the best candidate for manufacturing is computationally expensive. Therefore, an accurate and efficient printability estimation is crucial and can significantly accelerate the layout decomposition and MO (LDMO) flow. In this article, we propose a convolutional neural network (CNN)-based prediction and integrate it into our new high-performance LDMO framework. The optimization process can be considerably improved as the decomposition quality has been inferred in the early phase. To facilitate the network training and ensure better estimation accuracy, we develop sampling strategies for both layout and decomposition. Moreover, we enhance the layout sampling approach by adopting autoencoder to distance evaluation that promises superior sampling results. The experimental results demonstrate the effectiveness and the efficiency of the proposed algorithms. © 1982-2012 IEEE.

关键词： Manufacture

来源：评论

学校读者我要写书评

暂无评论

A Derivative Matrix-Based Covert Communication Method in Blockchain

引用

computer Systems Science & engineering 2023年第7期46卷 225-239页

作者： Xiang Zhang Xiaona Zhang Xiaorui Zhang Wei Sun Ruohan Meng Xingming Sun School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China School of Hydrology and Water Resources Nanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Key Laboratory of Hydrometeorological Disaster Mechanism andWarning ofMinistry ofWater Resources Nanjing210044China Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) NanjingUniversity of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Science Engineering Nanyang Technological UniversitySingapore

The data in the blockchain cannot be tampered with and the users are anonymous,which enables the blockchain to be a natural carrier for covert ***,the existing methods of covert communication in blockchain suffer from the predefined channel structure,the capacity of a single transaction is not high,and the fixed transaction behaviors will lower the concealment of the communication ***,this paper proposes a derivation matrix-based covert communication method in *** uses dual-key to derive two types of blockchain addresses and then constructs an address matrix by dividing addresses into multiple layers to make full use of the redundancy of ***,to solve the problem of the lack of concealment caused by the fixed transaction behaviors,divide the rectangular matrix into square blocks with overlapping regions and then encrypt different blocks sequentially to make the transaction behaviors of the channel addresses match better with those of the real ***,the linear congruence algorithm is used to generate random sequence,which provides a random order for blocks encryption,and thus enhances the security of the encryption *** results show that this method can effectively reduce the abnormal transaction behaviors of addresses while ensuring the channel transmission efficiency.

关键词： Covert communication blockchain concealment security capacity derivation

来源：评论

学校读者我要写书评

暂无评论

NBMon: NB-IoT-based UAV Network Routing Monitoring System 24

NBMon: NB-IoT-based UAV Network Routing Monitoring System

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data Science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Tang, Ji'ao Zhu, Xiaojun Dong, Chao Zhang, Lei College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics China Nanjing University State Key Laboratory of Novel Software Technology Nanjing China

ISBN: (纸本)9798350319934

The routing state of UAV networks is difficult to monitor, making many new routing protocols hard to evaluate on UAVs. In this paper, we propose NBMon, an NB-IoT-based routing monitoring system for UAV networks, which can upload the routing table information from the host device to a control station through the NB-IoT network. At the same time, the control station can also send commands to the monitored devices to change routes. However, one challenge is that both NB-IoT modules and the control station are behind NAT without global IP addresses. We propose a NAT traversal method on top of NB- IoT. It allows communication between the NB-IoT modules and the control station in different networks. Finally, we implement NBMon and evaluate the performance of NB-IoT devices through real-world experiments. © 2022 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

ML-based Privacy Leakage Behavior Detection in Android Apps at Scale 19

ML-based Privacy Leakage Behavior Detection in Android Apps ...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Bu, ZhiLiang Zhao, Chunlei Gong, Liangyi Wang, Yan Yang, Yi Wang, Xi Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Ministry of Education Tianjin China Tianjin University of Technology School of Computer Science and Engineering Tianjin China Computer Network Information Center Chinese Academy of Sciences Beijing China Southeast University School of Cyber Science and Engineering Nanjing China

ISBN: (纸本)9798350346558

In recent years, Android application privacy leaking issues frequently occur, with the results that privacy leakage detection becomes a critical role in app market security review, and numerous mobile apps have been removed from the app stores as a consequence. At the same time, manual review is still considered as a main method for market security audit, but it would cause low efficiency and high false positive when faced with thousands of auditing tasks. To overcome the above problems, this paper implements a large volume, automated detection of privacy leaks in Android applications via machine learning algorithms. In order to achieve a comprehensive and in-depth analysis of application behavior features, firstly, 2346 benign software from app market and 1912 malware identified by a national regulatory authority as leaking privacy in the past two years were selected and studied using a hybrid static-dynamic analysis. Then by developing novel sensitivity criteria, we opt privacy-sensitive key permissions and API calls that are highly relevant to privacy leakage behavior. Moreover, in order to improve the practicability of our system, this thesis systematically optimize the application exerciser on the Android emulator, and achieve average per-app analysis time with less than 2 minutes. Finally, the results of the comparison experiments reveal that the stacking ensemble learning algorithm displayed the best classification performance and achieved 97.81% in accuracy of privacy leakage behavior detection. © 2022 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

来源：评论

学校读者我要写书评

暂无评论

Reasoning about Strategic Abilities in Stochastic Multi-agent Systems

arXiv

引用

arXiv 2024年

作者： Zhang, Yedi Song, Fu Chen, Taolue Wu, Xuzhi Department of Computing Science National University of Singapore Singapore State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China School of Computing and Mathematical Sciences Birkbeck University of London United Kingdom College of Computer Science and Software Engineering Shenzhen University China

Reasoning about strategic abilities is key to AI systems comprising multiple agents, which provide a unified framework for formalizing various problems in game theory, social choice theory, etc. In this work, we propose a probabilistic extension of the alternating-time μ-calculus (AMC), named PAMC, for reasoning about the strategic abilities of agents in stochastic multi-agent systems. We show that PAMC subsumes two existing logics AMC and PμTL (a probabilistic extension of the modal μ-calculus), but is incomparable with the probabilistic alternating-time temporal logic (PATL). We study the problems of model checking and satisfiability checking for PAMC. We first give a model checking algorithm by leveraging algorithms for solving normal-form games and AMC model checking. We establish that the model checking problem of PAMC remains in UP∩co-UP, the same complexity class as the model checking problem for AMC and PμTL. We also provide a new reduction from the satisfiability problem of PAMC to solving parity games, by which we obtain an EXPTIME decision procedure, as well as the small model property which allows to construct a model for each satisfiable PAMC formula. Satisfiability in PAMC has the same complexity as in the modal μ-calculus, unlike PCTL and PATL whose satisfiability checking problems remain open. We have implemented both the model checking and satisfiability checking algorithms as open-source tools. Experimental results are reported, showcasing the practical applications and effectiveness of our approaches. © 2024, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

UR4NNV: Neural Network Verification, Under-approximation Reachability Works!

arXiv

引用

arXiv 2024年

作者： Liang, Zhen Wu, Taoran Zhao, Ran Xue, Bai Wang, Ji Yang, Wenjing Deng, Shaojun Liu, Wanwei College of Computer Science and Technology National University of Defense Technology China Institute of Software Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology China

Recently, formal verification of deep neural networks (DNNs) has garnered considerable attention, and over-approximation based methods have become popular due to their effectiveness and efficiency. However, these strategies face challenges in addressing the "unknown dilemma" concerning whether the exact output region or the introduced approximation error violates the property in question. To address this, this paper introduces the UR4NNV verification framework, which utilizes under-approximation reachability analysis for DNN verification for the first time. UR4NNV focuses on DNNs with Rectified Linear Unit (ReLU) activations and employs a binary tree branch-based under-approximation algorithm. In each epoch, UR4NNV under-approximates a sub-polytope of the reachable set and verifies this polytope against the given property. Through a trial-and-error approach, UR4NNV effectively falsifies DNN properties while providing confidence levels when reaching verification epoch bounds and failing falsifying properties. Experimental comparisons with existing verification methods demonstrate the effectiveness and efficiency of UR4NNV, significantly reducing the impact of the "unknown dilemma".MSC Codes 68Q60, 68T07 Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Mixture of Attention Heads: Selecting Attention Heads Per Token

Mixture of Attention Heads: Selecting Attention Heads Per To...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Zhang, Xiaofeng Shen, Yikang Huang, Zeyu Zhou, Jie Rong, Wenge Xiong, Zhang State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University China Sino-French Engineer School Beihang University China Mila University of Montreal Canada Wechat AI Tencent China

Mixture-of-Experts (MoE) networks have been proposed as an efficient way to scale up model capacity and implement conditional computing. However, the study of MoE components mostly focused on the feedforward layer in Transformer architecture. This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism. MoA includes a set of attention heads that each has its own set of parameters. Given an input, a router dynamically selects a subset of k attention heads per token. This conditional computation schema allows MoA to achieve stronger performance than the standard multi-head attention layer. Furthermore, the sparsely gated MoA can easily scale up the number of attention heads and the number of parameters while preserving computational efficiency. In addition to the performance improvements, MoA also automatically differentiates heads' utilities, providing a new perspective to discuss the model's interpretability. We conducted experiments on several important tasks, including Machine Translation and Masked Language Modeling. Experiments have shown promising results on several tasks against strong baselines that involve large and very deep models. © 2022 Association for Computational Linguistics.

关键词： Modeling languages

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：