检索结果-内蒙古大学图书馆

Modeling Inter-Intra Heterogeneity for Graph Federated Learning

学校读者我要写书评

暂无评论

arXiv 2024年

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 Jinan University China Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

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. Code is available at https://***/blgpb/FedIIH. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Cao, Hongye Feng, Fan Huo, Jing Yang, Shangdong Fang, Meng Yang, Tianpei Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University Nanjing210093 China Department of Electrical Engineering City University of Hong Kong Hong Kong School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Department of Computer Science University of Liverpool LiverpoolL69 3BX United Kingdom

Model-based offline Reinforcement Learning (RL) constructs environment models from offline datasets to perform conservative policy optimization. Existing approaches focus on learning state transitions through ensemble models, rollouting conservative estimation to mitigate extrapolation errors. However, the static data makes it challenging to develop a robust policy, and offline agents cannot access the environment to gather new data. To address these challenges, we introduce Model-based Offline Reinforcement learning with AdversariaL data augmentation (MORAL). In MORAL, we replace the fixed horizon rollout by employing adversaria data augmentation to execute alternating sampling with ensemble models to enrich training data. Specifically, this adversarial process dynamically selects ensemble models against policy for biased sampling, mitigating the optimistic estimation of fixed models, thus robustly expanding the training data for policy optimization. Moreover, a differential factor is integrated into the adversarial process for regularization, ensuring error minimization in extrapolations. This data-augmented optimization adapts to diverse offline tasks without rollout horizon tuning, showing remarkable applicability. Extensive experiments on D4RL benchmark demonstrate that MORAL outperforms other model-based offline RL methods in terms of policy learning and sample efficiency. © 2025, CC BY.

关键词： Adversarial machine learning

Image Data Augmentation for Deep Learning: A Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Suorong Xiao, Weikang Zhang, Mengchen Guo, Suhan Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data. As an effective way to improve the sufficiency and diversity of training data, data augmentation has become a necessary part of successful application of deep learning models on image data. In this paper, we systematically review different image data augmentation methods. We propose a taxonomy of reviewed methods and present the strengths and limitations of these methods. We also conduct extensive experiments with various data augmentation methods on three typical computer vision tasks, including semantic segmentation, image classification and object detection. Finally, we discuss current challenges faced by data augmentation and future research directions to put forward some useful research guidance. © 2022, CC BY.

关键词： computer vision

RandoMix: A Mixed Sample Data Augmentation Method with Multiple Mixed Modes

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Xiaoliang Shen, Furao Zhao, Jian Nie, Changhai State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Data augmentation plays a crucial role in enhancing the robustness and performance of machine learning models across various domains. In this study, we introduce a novel mixed-sample data augmentation method called RandoMix. RandoMix is specifically designed to simultaneously address robustness and diversity challenges. It leverages a combination of linear and mask mixed modes, introducing flexibility in candidate selection and weight adjustments. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands. Our results demonstrate its superior performance compared to existing techniques such as Mixup, CutMix, Fmix, and ResizeMix. Notably, RandoMix excels in enhancing model robustness against adversarial noise, natural noise, and sample occlusion. The comprehensive experimental results and insights into parameter tuning underscore the potential of RandoMix as a versatile and effective data augmentation method. Moreover, it seamlessly integrates into the training pipeline. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Prototype-Wise Self-Knowledge Distillation for Few-Shot Segmentation

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Chen, Yadang Xu, Xinyu Wei, Chenchen Yang, Zhi-Xin School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China The State Key Laboratory of Internet of Things for Smart City Department of Electromechanical Engineering University of Macau 999078 China

Few-shot segmentation was proposed to obtain segmentation results for a image with an unseen class by referring to a few labeled samples. However, due to the limited number of samples, many few-shot segmentation models suffer from poor generalization. Prototypical network-based few-shot segmentation still has issues with spatial inconsistency and prototype bias. Since the target class has different appearance in each image, some specific features in the prototypes generated from the support image and its mask do not accurately reflect the generalized features of the target class. To address the support prototype consistency issue, we put forward two modules: Data Augmentation Self-knowledge Distillation (DASKD) and Prototype-wise Regularization (PWR). The DASKD module focuses on enhancing spatial consistency by using data augmentation and self-knowledge distillation. Self-knowledge distillation helps the model acquire generalized features of the target class and learn hidden knowledge from the support images. The PWR module focuses on obtaining a more representative support prototype by conducting prototype-level loss to obtain support prototypes closer to the category center. Broad evaluation experiments on PASCAL-5i and COCO-20i demonstrate that our model outperforms the prior works on few-shot segmentation. Our approach surpasses the state of the art by 7.5% in PASCAL-5i and 4.2% in COCO-20i. © 2023, The Authors. All rights reserved.

关键词： Distillation

Sensitivity Pruner: Filter-Level Deep Neural Network Compression

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Guo, Suhan Lai, Bilan Yang, Suorong Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Department of Computer Science and Technology Nanjing University China School of Electronic Science and Engineering Nanjing University China

As neural networks get deeper to better higher performance, the demand for deployable models on resource-constrained devices also grows. In this work, we propose to achieve model compression using filter-level pruning, which eliminates less sensitive filters. The previous method evaluates neuron importance using the connection matrix gradient in a single shot, which is vulnerable to the sampling bias. Thus, we integrate this measure with the previously proposed "pruning while fine-tuning" framework. Besides classification errors, we introduce the difference between the learned pruning strategy and the single-shot strategy as the second loss component with a self-adjustive hyper-parameter that balances the training goal between improving accuracy and pruning more filters. Experimental results demonstrate the effectiveness of our Sensitivity Pruner (SP), which significantly reduces the computational cost and makes pruned models achieve comparable if not better performance on CIFAR10, CIFAR100, and ILSVRC-12 datasets. © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

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

学校读者我要写书评

暂无评论

SSRN

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

Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Shuhai Yang, Jiahao Luo, Hui Chen, Jie Wang, Li Liu, Feng Han, Bo Tan, Mingkui The School of Software Engineering South China University of Technology China the Pazhou Laboratory Guangzhou China The National Key Laboratory of Optical Field Manipulation Science and Technology CAS China the Institute of Optics and Electronics CAS Chengdu China the School of Electronic and Computer Engineering Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518066 China The Department of Mathematics The Department of Computer Science and Engineering University of Texas at Arlington ArlingtonTX76019 United States University of Melbourne Australia Department of Computer Science Hong Kong Baptist University Hong Kong

Deep neural networks (DNNs) are vulnerable to adversarial samples crafted by adding imperceptible perturbations to clean data, potentially leading to incorrect and dangerous predictions. Adversarial purification has been an effective means to improve DNNs robustness by removing these perturbations before feeding the data into the model. However, it faces significant challenges in preserving key structural and semantic information of data, as the imperceptible nature of adversarial perturbations makes it hard to avoid over-correcting, which can destroy important information and degrade model performance. In this paper, we break away from traditional adversarial purification methods by focusing on the clean data manifold. To this end, we reveal that samples generated by a well-trained generative model are close to clean ones but far from adversarial ones. Leveraging this insight, we propose Consistency Model-based Adversarial Purification (CMAP), which optimizes vectors within the latent space of a pre-trained consistency model to generate samples for restoring clean data. Specifically, 1) we propose a Perceptual consistency restoration mechanism by minimizing the discrepancy between generated samples and input samples in both pixel and perceptual spaces. 2) To maintain the optimized latent vectors within the valid data manifold, we introduce a Latent distribution consistency constraint strategy to align generated samples with the clean data distribution. 3) We also apply a Latent vector consistency prediction scheme via an ensemble approach to enhance prediction reliability. CMAP fundamentally addresses adversarial perturbations at their source, providing a robust purification. Extensive experiments on CIFAR-10 and ImageNet-100 show that our CMAP significantly enhances robustness against strong adversarial attacks while preserving high natural accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

MindSpore Quantum: A User-Friendly, High-Performance, and AI-Compatible Quantum Computing Framework

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Xusheng Cui, Jiangyu Cui, Zidong He, Runhong Li, Qingyu Li, Xiaowei Lin, Yanling Liu, Jiale Liu, Wuxin Lu, Jiale Luo, Maolin Lyu, Chufan Pan, Shijie Pavel, Mosharev Shu, Runqiu Tang, Jialiang Xu, Ruoqian Xu, Shu Yang, Kang Yu, Fan Zeng, Qingguo Zhao, Haiying Zheng, Qiang Zhou, Junyuan Zhou, Xu Zhu, Yikang Zou, Zuoheng Bayat, Abolfazl Cao, Xi Cui, Wei Li, Zhendong Long, Guilu Su, Zhaofeng Wang, Xiaoting Wang, Zizhu Wei, Shijie Wu, Re-Bing Zhang, Pan Yung, Man-Hong MindSpore Quantum Special Interest Group Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu610051 China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100190 China Institute for Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China School of Computer Science and Technology University of Science and Technology of China Hefei230027 China School of Automation Science and Engineering South China University of Technology Guangzhou510641 China Department of Physical Chemistry University of the Basque Country UPV/EHU Apartado 644 Bilbao48080 Spain School of Physics and Astronomy Sun Yat-sen University Zhuhai519082 China Key Laboratory of Quantum Physics and Photonic Quantum Information Ministry of Education University of Electronic Science and Technology of China Chengdu611731 China Department of Automation Tsinghua University Beijing100084 China Key Laboratory of Theoretical and Computational Photochemistry Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Beijing Academy of Quantum Information Sciences Beijing100193 China State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Tsinghua University Beijing100084 China CAS Key Laboratory for Theoretical Physics Institute of Theoretical Physics Chinese Academy of Sciences Beijing100190 China Shenzhen International Quantum Academy Shenzhen518048 China Guangdong Provincial Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China Shenzhen Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen518055 China

We introduce MindSpore Quantum, a pioneering hybrid quantum-classical framework with a primary focus on the design and implementation of noisy intermediate-scale quantum (NISQ) algorithms. Leveraging the robust support of MindSpore, an advanced open-source deep learning training/inference framework, MindSpore Quantum exhibits exceptional efficiency in the design and training of variational quantum algorithms on both CPU and GPU platforms, delivering remarkable performance. Furthermore, this framework places a strong emphasis on enhancing the operational efficiency of quantum algorithms when executed on real quantum hardware. This encompasses the development of algorithms for quantum circuit compilation and qubit mapping, crucial components for achieving optimal performance on quantum processors. In addition to the core framework, we introduce QuPack-a meticulously crafted quantum computing acceleration engine. QuPack significantly accelerates the simulation speed of MindSpore Quantum, particularly in variational quantum eigensolver (VQE), quantum approximate optimization algorithm (QAOA), and tensor network simulations, providing astonishing speed. This combination of cutting-edge technologies empowers researchers and practitioners to explore the frontiers of quantum computing with unprecedented efficiency and performance. © 2024, CC BY.

关键词： Quantum computers