检索结果-内蒙古大学图书馆

Comprehensive Architecture Search for Deep Graph Neural Networks

IEEE Transactions on big data 2025年

作者： Dong, Yukang Pan, Fanxing Gui, Yi Jiang, Wenbin Wan, Yao Zheng, Ran Jin, Hai National Engineering Research Center for Big Data Technology Huazhong University of Science and Technology Wuhan430074 China Huazhong University of Science and Technology Service Computing Technology and System Laboratory Wuhan430074 China Huazhong University of Science and Technology Cluster and Grid Computing Laboratory Wuhan430074 China Huazhong University of Science and Technology School of Computer Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China

In recent years, Neural Architecture Search (NAS) has emerged as a promising approach for automatically discovering superior model architectures for deep Graph Neural Networks (GNNs). Different methods have paid attention to different types of search spaces. However, due to the time-consuming nature of training deep GNNs, existing NAS methods often fail to explore diverse search spaces sufficiently, which constrains their effectiveness. To crack this hard nut, we propose CAS-DGNN, a novel comprehensive architecture search method for deep GNNs. It encompasses four kinds of search spaces that are the composition of aggregate and update operators, different types of aggregate operators, residual connections, and hyper-parameters. To meet the needs of such a complex situation, a phased and hybrid search strategy is proposed to accommodate the diverse characteristics of different search spaces. Specifically, we divide the search process into four phases, utilizing evolutionary algorithms and Bayesian optimization. Meanwhile, we design two distinct search methods for residual connections (All-connected search and Initial Residual search) to streamline the search space, which enhances the scalability of CAS-DGNN. The experimental results show that CAS-DGNN achieves higher accuracy with competitive search costs across ten public datasets compared to existing methods. © 2015 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Fil-Cad: A Fault Detection Method for Iiot Based on Federated Incremental Learning with Class Accuracy Distillation

SSRN

引用

SSRN 2024年

作者： Liu, Yanhua Fang, Wenyu Huang, Wei Wang, Xiaofeng Zhao, Baokang Liu, Ximeng College of Computer and Data Science Fuzhou University Fuzhou350108 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350108 China College of Computer National University of Defense Technology Changsha410073 China

Fault detection is a research topic attracting much attention in IIoT. However, the continuous accumulation and growth of IIoT data leads to the catastrophic forgetting problem in the fault detection model and data heterogeneity, which creates a bottleneck for the performance and generalization of federated learning in fault detection. To improve the fault detection performance of federated learning models in data incremental scenarios, we propose a federatedincremental-learning-based fault detection method for IIoT, namely FIL-CAD. Firstly, comparing the knowledge distillation, the accuracies of different data classes in the global and local models are chosen as the model lightweight learning features, and the loss function is weighted. Secondly, we introduce the concept of data learning depth. It computes different model weights in the aggregation based on their degrees of data sample learning and model training participation and obtains the global model through weighted aggregation. Additionally, FIL-CAD supports the combination of differential privacy to protect data privacy. The proposed method is compared with four benchmark methods on four datasets, which include CWRU and MFPT bearing datasets. Then, the experimental results show that FIL-CAD performs optimally in accuracy and F1-Score, and the average accuracy is improved by 1.32%-18.52%, demonstrating the superiority of FIL-CAD. © 2024, The Authors. All rights reserved.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

CFT Constraints on Parity-odd Interactions with Axions and Dilatons

arXiv

引用

arXiv 2024年

作者： Corianò, Claudio Lionetti, Stefano Dipartimento di Matematica e Fisica Università del Salento INFN Sezione di Lecce Via Arnesano Lecce73100 Italy National Center for HPC Big Data and Quantum Computing Via Magnanelli 2 Casalecchio di Reno40033 Italy Lecce73100 Italy

We illustrate how the conformal Ward identities (CWIs) in momentum space completely determine the structure of a parity-odd 3-point correlator involving currents, energy-momentum tensors and at least one scalar operator in d = 4. Conformal invariance fixes almost all such possible correlators to vanish. The only exceptions are given by the 〈JJO〉odd and the 〈TTO〉odd which in momentum space are protected by chiral and conformal anomalies. Specifically, one can obtain a non-vanishing solution by considering scalar operators such as O = ∇ · JA, O = gµνTµν or their shadow transforms. We comment on the implications of these results that constrain the coupling of axions and dilatons in a conformal phase of the early universe. Copyright © 2024, The Authors. All rights reserved.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. China Cluster and Grid Computing Lab. China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Robust and Lightweight Authentication for Securing Communication in the Internet-of-Drones (IoD) Environment

Robust and Lightweight Authentication for Securing Communica...

引用

IEEE Conference on Computer Communications Workshops, INFOCOM Wksps

作者： Saeed Ullah Jan Muhammad Bilal Anwar Ghani Salabat Khan Rashid Ahmad Do–Hveun Kim Higher Education Department Govt. College Wari (Dir Upper) Khyber Pakhtunkhwa Pakistan School of Computing and Communications Lancaster University United Kingdom Big Data Research Center Jeju National University Jeju-si South Korea Faculty of Computing and Information Technology Sohar University Sohar Oman Dept. Computer Engineering Jeju National University Jeju-si South Korea

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

Being an essential component of 5G and beyond, the Internet of Drones (IoD) enables a legitimate operator to employ several drones to carry out distinct missions in restricted airspace under the control of the GCS. Communication with the external user (mobile operator), the central server, and other drones is accomplished via a public wireless medium, which is vulnerable to numerous threats and needs robust authentication. Various authentication schemes have been presented, some of which have design issues, excessive communication, or lack of a delicate balance of security and performance due to modular exponentiation. Therefore, this article proposes a secure authentication scheme based on asymmetric cryptography to address the issues above. The security of the proposed scheme is formally scrutinized through the RoR model, ProVerif. Furthermore, the performance is analyzed through computation, communication, and storage overheads. The comparative analysis shows that the proposed scheme balances security with performance and can be implemented in a real-world IoD environment.

关键词： Wireless communication Hash functions Protocols Computational modeling Authentication Product delivery Internet

来源：评论

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning 39

FedAA: A Reinforcement Learning Perspective on Adaptive Aggr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Jialuo Chen, Wei Zhang, Xiaojin 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 Wuhan430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)157735897X

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Axion-like Interactions and CFT in Topological Matter, Anomaly Sum Rules and the Faraday Effect

arXiv

引用

arXiv 2024年

作者： Corianò, Claudio Cretì, Mario Lionetti, Stefano Melle, Dario Tommasi, Riccardo Dipartimento di Matematica e Fisica Università del Salento INFN Sezione di Lecce Via Arnesano Lecce73100 Italy National Center for HPC Big Data and Quantum Computing Lecce73100 Italy Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Via Barsanti 14 Arnesano Lecce73010 Italy

We discuss fundamental aspects of chiral anomaly-driven interactions in conformal field theory (CFT) in four spacetime dimensions. They find application in very general contexts, from early universe plasma to topological condensed matter. We outline the key shared characteristics of these interactions, specifically addressing the case of chiral anomalies, both for vector currents and gravitons. In the case of topological materials, the gravitational chiral anomaly is generated by thermal gradients via the (Tolman-Ehrenfest) Luttinger relation. In the CFT framework, a nonlocal effective action, derived through perturbation theory, indicates that the interaction is mediated by an excitation in the form of an anomaly pole, which appears in the conformal limit of the vertex. To illustrate this, we demonstrate how conformal Ward identities (CWIs) in momentum space allow us to reconstruct the entire chiral anomaly interaction in its longitudinal and transverse sectors just by inclusion of a pole in the longitudinal sector. Both sectors are coupled in amplitudes with an intermediate chiral fermion or a bilinear Chern-Simons current with intermediate photons. In the presence of fermion mass corrections, the pole transforms into a cut, but the absorption amplitude in the axial-vector channel satisfies mass-independent sum rules related to the anomaly in any chiral interaction. The detection of an axion-like/quasiparticle in these materials may rely on a combined investigation of these sum rules, along with the measurement of the angle of rotation of the plane of polarization of incident light when subjected to a chiral perturbation. This phenomenon serves as an analogue of a similar one in ordinary axion physics, in the presence of an axion-like condensate, that we rederive using axion electrodynamics. Copyright © 2024, The Authors. All rights reserved.

关键词： Perturbation techniques

来源：评论

学校读者我要写书评

暂无评论

Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking 25

Towards high-throughput and low-latency billion-scale vector...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Bing Tian Haikun Liu Yuhang Tang Shihai Xiao Zhuohui Duan Xiaofei Liao Hai Jin Xuecang Zhang Junhua Zhu Yu Zhang National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present Fusion-ANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of Fusion-ANNS lies in CPU/GPU collaborative filtering and reranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN; 2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated data Visualization from Natural Language via Large Language Models: An Exploratory Study

arXiv

引用

arXiv 2024年

作者： Wu, Yang Wan, Yao Zhang, Hongyu Sui, Yulei Wei, Wucai Zhao, Wei Xu, Guandong Jin, Hai Huazhong University of Science and Technology China Chongqing University China University of New South Wales Australia University of Technology Sydney Australia 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 Wuhan430074 China

The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insights from vast amounts of data. Recently, many deep learning-based approaches have been developed for NL2Vis. Despite the considerable efforts made by these approaches, challenges persist in visualizing data sourced from unseen databases or spanning multiple tables. Taking inspiration from the remarkable generation capabilities of Large Language Models (LLMs), this paper conducts an empirical study to evaluate their potential in generating visualizations, and explore the effectiveness of in-context learning prompts for enhancing this task. In particular, we first explore the ways of transforming structured tabular data into sequential text prompts, as to feed them into LLMs and analyze which table content contributes most to the NL2Vis. Our findings suggest that transforming structured tabular data into programs is effective, and it is essential to consider the table schema when formulating prompts. Furthermore, we evaluate two types of LLMs: finetuned models (e.g., T5-Small) and inference-only models (e.g., GPT-3.5), against state-of-the-art methods, using the NL2Vis benchmarks (i.e., nvBench). The experimental results reveal that LLMs outperform baselines, with inference-only models consistently exhibiting performance improvements, at times even surpassing fine-tuned models when provided with certain few-shot demonstrations through in-context learning. Finally, we analyze when the LLMs fail in NL2Vis, and propose to iteratively update the results using strategies such as chain-of-thought, role-playing, and code-interpreter. The experimental results confirm the efficacy of iterative updates and hold great potential for future study. © 2024, CC BY.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

DarkFed: A data-Free Backdoor Attack in Federated Learning

arXiv

引用

arXiv 2024年

作者： Li, Minghui Wan, Wei Ning, Yuxuan Hu, Shengshan Xue, Lulu Zhang, Leo Yu Wang, Yichen School of Software Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simplest defense suffices to defend against the state-of-the-art attack, 3DFed. A practical FL backdoor attack remains in a nascent stage of development. To bridge this gap, we present DarkFed. Initially, we emulate a series of fake clients, thereby achieving the attacker proportion typical of academic research scenarios. Given that these emulated fake clients lack genuine training data, we further propose a data-free approach to backdoor FL. Specifically, we delve into the feasibility of injecting a backdoor using a shadow dataset. Our exploration reveals that impressive attack performance can be achieved, even when there is a substantial gap between the shadow dataset and the main task dataset. This holds true even when employing synthetic data devoid of any semantic information as the shadow dataset. Subsequently, we strategically construct a series of covert backdoor updates in an optimized manner, mimicking the properties of benign updates, to evade detection by defenses. A substantial body of empirical evidence validates the tangible effectiveness of DarkFed. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

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：