检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zhuo, Jiaming Lu, Yintong Ning, Hui Fu, Kun Niu, Bingxin He, Dongxiao Wang, Chuan Guo, Yuanfang Wang, Zhen Cao, Xiaochun Yang, Liang Hebei Province Key Laboratory of Big Data Calculation School of Artificial Intelligence Hebei University of Technology Tianjin China College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science and Technology Beijing JiaoTong University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Cybersecurity Northwestern Polytechnical University Xi'an China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen China

In real-world scenarios, networks (graphs) and their tasks possess unique characteristics, requiring the development of a versatile graph augmentation (GA) to meet the varied demands of network analysis. Unfortunately, most Graph Contrastive Learning (GCL) frameworks are hampered by the specificity, complexity, and incompleteness of their GA techniques. Firstly, GAs designed for specific scenarios may compromise the universality of models if mishandled. Secondly, the process of identifying and generating optimal augmentations generally involves substantial computational overhead. Thirdly, the effectiveness of the GCL, even the learnable ones, is constrained by the finite selection of GAs available. To overcome the above limitations, this paper introduces a novel unified GA module dubbed UGA after reinterpreting the mechanism of GAs in GCLs from a message-passing perspective. Theoretically, this module is capable of unifying any explicit GAs, including node, edge, attribute, and subgraph augmentations. Based on the proposed UGA, a novel generalized GCL framework dubbed Graph cOntrastive UnifieD Augmentations (GOUDA) is proposed. It seamlessly integrates widely adopted contrastive losses and an introduced independence loss to fulfill the common requirements of consistency and diversity of augmentation across diverse scenarios. Evaluations across various datasets and tasks demonstrate the generality and efficiency of the proposed GOUDA over existing state-of-the-art GCLs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Based Unified Framework for Multidimensional Biological Age Estimation

SSRN

引用

SSRN 2024年

作者： Yu, Qi Da, Lijuan Ma, Qian Huang, Yushu Dong, Yue Liu, Yuan Li, Xiaoyu Wu, Xifeng Li, Zilin Li, Wenyuan Center of Clinical Big Data and Analytics The Second Affiliated Hospital Department of Big Data in Health Science School of Public Health Zhejiang University School of Medicine Zhejiang Hangzhou China Zhejiang Provincial Key Laboratory of Intelligent Preventive Medicine China School of Social Sciences Tsinghua University Beijing China School of Mathematics and Statistics Northeast Normal University Jilin Changchun China

Objective: Aging varies between individuals as well as between organs within an individual. This study aims to develop a machine learning-based unified framework to comprehensively assess and interpret biological aging, where each base component is used to assess the health status of different organ systems. Method: 264,874 individuals at baseline from the UK biobank were included. The ensemble model was constructed to estimate biological age (BA) by combining the predictions of different base models, where the base models estimated organ health using organ-specific data. Phenome-wide association study (PheWAS) and Cox proportional-hazards models were used to assess the associations between various BA accelerations (the contrast between BA and chronological age (CA)) and the risk of aging-related morbidity and mortality. Causal mediation analysis was performed to investigate the mediated effect of biological aging in the association between lifestyle/environmental factors and all-cause mortality. Result: Our estimated BA was significantly correlated with CA in relatively healthy individuals (mean absolute error (MAE): 4.480 years;Pearson correlation: 0.717, P © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

computing optimal partition problems via Lagrange multiplier approach

arXiv

引用

arXiv 2024年

作者： Cheng, Qing Guo, Jing Wang, Dong Department of Mathematics Tongji University Shanghai200092 China Key Laboratory of Intelligent Computing and Applications Tongji University Ministry of Education China School of Science and Engineering The Chinese University of Hong Kong Guangdong Shenzhen518172 China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data Guangdong518172 China

In this paper, we consider numerical approximations for the optimal partition problem using Lagrange multipliers. By rewriting it into constrained gradient flows, three and four steps numerical schemes based on the Lagrange multiplier approach [16, 17] are proposed to solve the constrained gradient system. Numerical schemes proposed for the constrained gradient flows satisfy the nice properties of orthogonality-preserving, norm-preserving, positivity-preserving and energy dissipating. The proposed schemes are very efficient in which only linear Poisson equations are solved at each time step. Extensive numerical results in 2D and 3D for optimal partition problem are presented to validate the effectiveness and accuracy of the proposed numerical schemes. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Transfer Neural Architecture Search Across Spaces via Representation Learning

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Hou, Boyu Feng, Liang Chen, Xuefeng Tang, Jing Tan, Kay Chen Liao, Xiaofeng Chongqing University College of Computer Science China Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing Chongqing400044 China The Hong Kong Polytechnic University Department of Data Science and Artificial Intelligence Hong Kong999077 Hong Kong Data Science and Analytics Thrust Guangzhou511453 China

Neural Architecture Search (NAS) has emerged as a crucial method for automating the design of deep learning models. Despite its potential, NAS frequently requires substantial computational and hardware resources. To mitigate these challenges, transferable NAS (TNAS) has been introduced, leveraging prior NAS results to enhance performance on new tasks. However, existing methods largely focus on knowledge transfer within identical neural search spaces, overlooking the potential for cross-domain transferability. Motivated by this gap, we explore evolutionary TNAS across heterogeneous search spaces by learning common neural representations. In particular, we introduce a novel approach that encodes both operational and topological information of neural architectures into a unified sequence using a simple tokenizer. This sequence is then processed by a variational auto-encoder, with a Transformer-based encoder to capture rich neural representations and a decoder that reconstructs the original sequence. By utilizing these latent representations, we further establish an inter-domain mapping that acts as a bridge, enabling effective explicit solution transfer among diverse search spaces to enhance the evolutionary NAS process. To harness this capability, we develop an evolutionary sequential transfer optimization approach that transfers knowledge during population initialization, providing both flexibility and adaptability. To the best of our knowledge, this work serves as the first attempt in the literature exploring evolutionary TNAS across diverse spaces. Moreover, we demonstrate the utility of our method through comprehensive empirical studies using different architecture spaces, including NAS-Bench-101, NAS-Bench-201, and the DARTS search space. Our results show that the proposed method significantly enhances the adaptability and performance of NAS across varied domains. © 1997-2012 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Validating SMT Solvers via Skeleton Enumeration Empowered by Historical Bug-Triggering Inputs

Validating SMT Solvers via Skeleton Enumeration Empowered by...

引用

International Conference on Software Engineering (ICSE)

作者： Maolin Sun Yibiao Yang Ming Wen Yongcong Wang Yuming Zhou Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Services Computing Technology and System Lab Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security National Engineering Research Center for Big Data Technology and System State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Technology Huazhong University of Science and Technology China

SMT solvers check the satisfiability of logic formulas over first-order theories, which have been utilized in a rich number of critical applications, such as software verification, test case generation, and program synthesis. Bugs hidden in SMT solvers would severely mislead those applications and further cause severe consequences. Therefore, ensuring the reliability and robustness of SMT solvers is of critical importance. Although many approaches have been proposed to test SMT solvers, it is still a challenge to discover bugs effectively. To tackle such a challenge, we conduct an empirical study on the historical bug-triggering formulas in SMT solvers' bug tracking systems. We observe that the historical bug-triggering formulas contain valuable skeletons (i.e., core structures of formulas) as well as associated atomic formulas which can cast significant impacts on formulas' ability in triggering bugs. Therefore, we propose a novel approach that utilizes the skeletons extracted from the historical bug-triggering formulas and enumerates atomic formulas under the guidance of association rules derived from historical formulas. In this study, we realized our approach as a practical fuzzing tool HistFuzz and conducted extensive testing on the well-known SMT solvers Z3 and cvc5. To date, HistFuzz has found 111 confirmed new bugs for Z3 and cvc5, of which 108 have been fixed by the developers. More notably, out of the confirmed bugs, 23 are soundness bugs and invalid model bugs found in the solvers' default mode, which are essential for SMT solvers. In addition, our experiments also demonstrate that HistFuzz outperforms the state-of-the-art SMT solver fuzzers in terms of achieved code coverage and effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Globally Consistent Vertical Federated Graph Autoencoder for Privacy-Preserving Community Detection 17th

Globally Consistent Vertical Federated Graph Autoencoder for...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Fang, Yutong Huang, Qingqing Ye, Enjie Guo, Wenzhong Guo, Kun Chen, Xiaoqi Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China College of Computer and Data Science/College of Software Fuzhou University Fuzhou350108 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789819923557

Community detection is a trendy area in research on complex network analysis and has a wide range of real-world applications, like advertising. As people become increasingly concerned about privacy, protecting participants’ privacy in distributed community detection has become a new challenge. When applied to not identically and independently distributed (Non-IID) data, most federated graph algorithms suffer from the weight divergence problem caused by diversified training of local and global models, resulting in accuracy degradation. Furthermore, the privacy protection approaches based on anonymization, such as differential privacy (DP), and cryptography, such as homomorphic encryption (HE), incur accuracy loss and high time consumption, respectively. In this paper, we propose a globally consistent vertical federated graph autoencoder (GCVFGAE) algorithm, which builds a globally consistent model among the coordinator and all participants to solve the Non-IID graph data problem. As well, an attribute blinding strategy based on security aggregation is developed to protect the network privacy of each participant without losing accuracy. Both real-world and artificial networks’ experiments show that our algorithm reaches higher accuracy than the existing vertical federated graph neural networks (GNNs) and the simple distributed graph autoencoder without federated learning and detects communities identical to those found by the standard graph autoencoder (GAE). © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Population dynamics

来源：评论

学校读者我要写书评

暂无评论

RGB-D Based Visual Navigation Using Direction Estimation Module 18th

RGB-D Based Visual Navigation Using Direction Estimation Mod...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Luo, Chao Bi, Sheng Dong, Min Nie, Hongxu School of Computer Science and Engineering South China University of Technology Guangdong Guangzhou510006 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangdong Guangzhou510006 China

ISBN: (纸本)9783030893699

Target-driven visual navigation without mapping works to solve navigation problems that given a target object, mobile robots can navigate to the target object. Recently, visual navigation has been researched and improved largely by learning-based methods. However, their methods lack depth information and spatial perception, using only single RGB images. To overcome these problems, two methods are presented in this paper. Firstly, we encode visual features of objects by dynamic graph convolutional network and extract 3D spatial features for objects by 3D geometry, a high level visual feature for agent to easily understand object relationship. Secondly, as human beings, they solve this problem in two steps, first exploring a new environment to find the target object and second planning a path to arrive. Inspired by the way of humans navigation, we propose direction estimation module (DEM) based on RGB-D images. DEM provides direction estimation of the target object to our learning model by a wheel odometry. Given a target object, first stage, our agent explores an unseen scene to detect the target object. Second stage, when detected the target object, we can estimate current location of the target object by 3D geometry, after that, each step of the agent, DEM will estimate new location of target object, and give direction information of the target object from a first-view image. It can guide our agent to navigate to the target object. Our experiment results outperforms the result of state of the art method in the artificial environment AI2-Thor. © 2021, Springer Nature Switzerland AG.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

EEG-GNet: GCN-Based EEG Signal Fatigue Detection Network for Edge Devices

EEG-GNet: GCN-Based EEG Signal Fatigue Detection Network for...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Fuquan Wu, Yu Xu, Xinxin Wang, Chuansheng Ma, Minjia Grau, Antoni Huang, Jiayan School of Computer and Big Data Minjiang University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of New Engineering Industry Putian University Putian China Department of Automatic Control Polytechnic University of Catalonia Barcelona Spain School of Robotics Xi'an Jiaotong-Liverpool University Suzhou China College of New Engineering Industry Putian University Fujian Ruituo Information Technology Limited Company Putian China

ISBN: (纸本)9798350386226

Fatigue driving is a common potential traffic safety hazard. To detect and analysis the driver Fatigue degree in real-time, more attention have been increasing paid to application research of EEG fatigue detection device. However, existing methods suffer from complex model structure or large-scale model parameters. In the other words, they requires high computational consumption and large memory footprint, which creates a contradiction between model and portable EEG machine with limited hardware resources. In this work, we take both time and frequency domains of EEG signal into account and design an lightweight and efficient driver fatigue detection network based on GCN (EEG-GNet), which is available edge-end device application. Experiments on 4th Raspberry Pi on a public baseline dataset show that our EEG-GNet outperforms the state-of-the-art methods and takes good tradeoff between detection accuracy and resource consumption. Our EEG-GNet provides a new potential opportunity for future applications in practical portable/wearable (P/W) devices. © 2024 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Global Enhanced Frame Prompt Tuning for Sound Event Detection

Global Enhanced Frame Prompt Tuning for Sound Event Detectio...

引用

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

作者： Shiyu Yu Lijian Gao Qirong Mao School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Sound Event Detection (SED) often employs pre-trained models to address data scarcity issues. However, existing systems usually treat the pretrained models as frozen feature extractors, resulting in suboptimal efficiency, or fully fine-tune the pretrained models, which requires substantial computational resources. To fully leverage the knowledge from pretrained models, we propose a novel Global Enhanced Frame Prompt Tuning (GE-FPT) framework, providing global and local insights tailored for SED tasks. Additionally, Frame Prompt Tuning (FPT) is proposed in our GE-FPT to effectively explore local temporal information, i.e., temporal details and context, which is essential for SED tasks, and in particular, for precise event boundary detection. Extensive experiments claim that our approach significantly outperforms full fine-tuning methods while substantially reducing computational costs. Our system achieves new state-of-the-art results, with PSDS1/PSDS2 scores of 0.628/0.845 on the DCASE2023 Challenge Task4 dataset. The source code is publicly available 1 .

关键词： Event detection Computational modeling Source coding Signal processing Feature extraction data models Acoustics Computational efficiency Speech processing Tuning

来源：评论

学校读者我要写书评

暂无评论

Di-Net: Decomposed Implicit Garment Transfer Network for Digital Clothed 3d Human

SSRN

引用

SSRN 2024年

作者： Zhong, Xiaojing Su, Yukun Wu, Zhonghua Lin, Guosheng Wu, Qingyao School of Software Engineering South China University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Peng Cheng Laboratory China Tencent Wechat Department China SenseTime Research

3D virtual try-on tasks aim to generate realistic try-on results for full- body garments, allowing them to be observed from arbitrary perspectives. Recent methods often represent the 3D human form with a fixed topol- ogy, limiting garment representation and leading to higher computational demands. Furthermore, the challenge of flexible transfer over various body parts remains. To address these problems, we introduce DI-Net(Decomposed Implicit Garment Transfer Network), where garment transfer is decomposed into 2D image layout transfer and 3D texture layout transfer. We propose a complementary warping module that leverages dense correspondence learn- ing and sparse flow learning to align the body appearance and garments with the target pose for image layout transfer. Subsequently, the transferred garments are lifted to the 3D human mesh by constructing a pixel-aligned implicit function and predicting the texture based on geometric priors. By applying different semantic masks for garment transfer, we efficiently control the texture of the generated mesh. Experimental results show the effective- ness and superiority of our method in the 3D virtual try-on task. © 2024, The Authors. All rights reserved.

关键词： Textures

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：