检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Chen, Xiuwei Chang, Xiaobin School of Artificial Intelligence Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Class incremental learning (CIL) aims to recognize both the old and new classes along the increment tasks. Deep neural networks in CIL suffer from catastrophic forgetting and some approaches rely on saving exemplars from previous tasks, known as the exemplar-based setting, to alleviate this problem. On the contrary, this paper focuses on the Exemplar-Free setting with no old class sample preserved. Balancing the plasticity and stability in deep feature learning with only supervision from new classes is more challenging. Most existing Exemplar-Free CIL methods report the overall performance only and lack further analysis. In this work, different methods are examined with complementary metrics in greater detail. Moreover, we propose a simple CIL method, Rotation Augmented Distillation (RAD), which achieves one of the top-tier performances under the Exemplar-Free setting. Detailed analysis shows our RAD benefits from the superior balance between plasticity and stability. Finally, more challenging exemplar-free settings with fewer initial classes are undertaken for further demonstrations and comparisons among the state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Residual Classifier for Class Incremental Learning

arXiv

引用

arXiv 2023年

作者： Chen, Xiuwei Chang, Xiaobin School of Artificial Intelligence Sun Yat-Sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The rehearsal strategy is widely used to alleviate the catastrophic forgetting problem in class incremental learning (CIL) by preserving limited exemplars from previous tasks. With imbalanced sample numbers between old and new classes, the classifier learning can be biased. Existing CIL methods exploit the long-tailed (LT) recognition techniques, e.g., the adjusted losses and the data re-sampling methods, to handle the data imbalance issue within each increment task. In this work, the dynamic nature of data imbalance in CIL is shown and a novel Dynamic Residual Classifier (DRC) is proposed to handle this challenging scenario. Specifically, DRC is built upon a recent advance residual classifier with the branch layer merging to handle the model-growing problem. Moreover, DRC is compatible with different CIL pipelines and substantially improves them. Combining DRC with the model adaptation and fusion (MAF) pipeline, this method achieves state-of-the-art results on both the conventional CIL and the LT-CIL benchmarks. Extensive experiments are also conducted for a detailed analysis. The code is publicly available Copyright © 2023, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Fault Estimation for Nonlinear Systems with Disturbance Based on Reinforcement Iterative Learning Strategy

Fault Estimation for Nonlinear Systems with Disturbance Base...

引用

data Driven Control and Learning Systems (DDCLS)

作者： Zhengquan Chen Ruirui Huang Zhiheng Zhang Yandong Hou School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Artificial Intelligence Henan University Zhengzhou China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

This paper addresses the problem of low fault estimation accuracy in Lipschitz nonlinear systems with external disturbances, presenting an innovative strategy based on a Reinforcement Iterative Learning (RIL) framework. Initially, we conducted precise mathematical modeling, comprehensively considering the impact of Lipschitz non-linearity and external disturbances. Subsequently, an iterative learning fault observer was designed, and the optimization problem for its parameters was reformulated into a reinforcement learning task, clearly defining the states, actions, and reward functions. Employing the Advantage Actor-Critic (A2C) reinforcement learning method, we optimized the gain parameters of the iterative learning fault estimator to approximate non-linearity. Simultaneously, with the increase in iteration count, the neural network weights were continually optimized, achieving accurate fault estimation. Experimental results demonstrate a significant improvement in fault estimation using the proposed method.

关键词： Sufficient conditions Accuracy Neural networks Estimation Reinforcement learning Observers Iterative methods

来源：评论

学校读者我要写书评

暂无评论

GraphLoRA: Structure-Aware Contrastive Low-Rank Adaptation for Cross-Graph Transfer Learning

arXiv

引用

arXiv 2024年

作者： Yang, Zhe-Rui Han, Jindong Wang, Chang-Dong Liu, Hao CSE Sun Yat-sen University Guangzhou China Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China EMIA HKUST Hong Kong CSE HKUST Hong Kong

Graph Neural Networks (GNNs) have demonstrated remarkable proficiency in handling a range of graph analytical tasks across various domains, such as e-commerce and social networks. Despite their versatility, GNNs face significant challenges in transferability, limiting their utility in real-world applications. Existing research in GNN transfer learning overlooks discrepancies in distribution among various graph datasets, facing challenges when transferring across different distributions. How to effectively adopt a well-trained GNN to new graphs with varying feature and structural distributions remains an under-explored problem. Taking inspiration from the success of Low-Rank Adaptation (LoRA) in adapting large language models to various domains, we propose GraphLoRA, an effective and parameter-efficient method for transferring well-trained GNNs to diverse graph domains. Specifically, we first propose a Structure-aware Maximum Mean Discrepancy (SMMD) to align divergent node feature distributions across source and target graphs. Moreover, we introduce low-rank adaptation by injecting a small trainable GNN alongside the pre-trained one, effectively bridging structural distribution gaps while mitigating the catastrophic forgetting. Additionally, a structure-aware regularization objective is proposed to enhance the adaptability of the pre-trained GNN to target graph with scarce supervision labels. Extensive experiments on eight real-world datasets demonstrate the effectiveness of GraphLoRA against fourteen baselines by tuning only 20% of parameters, even across disparate graph domains. The code is available at https://***/AllminerLab/GraphLoRA. © 2024, CC BY.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Homophily Induced Contrastive Attributed Graph Clustering

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Man-Sheng Lai, Pei-Yuan Liao, De-Zhang Wang, Chang-Dong Lai, Jian-Huang Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Guangxi Zhuang Autonomous Region Information Center Guangxi Key Laboratory of Digital Infrastructure Nanning China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China South China Technology Commercialization Center Guangzhou China Guangdong Key Laboratory of Information Security Technology Guangzhou China

Attributed graph clustering, aiming to discover the underlying graph structure and partition the graph nodes into several disjoint categories, is a basic task in graph data analysis. Although recent efforts over graph contrastive clustering have achieved decent performances, most of them get accustomed to construct the positive neighbor set by the generated pseudo clustering information, directly ignoring the ready-made neighbor nodes and the underlying semantics of edges in a graph. How to well deal with the graph neighbor-specific information to facilitate the performance of graph contrastive clustering is still a challenging problem. Therefore, in this work, we propose a novel Homophily Induced Contrastive Attributed Graph Clustering (HomoCAGC) method, where the power of homophily is exploited in facilitating the performance of contrastive attributed graph clustering, while the pseudo homophily in a graph is also explored and distinguished. Especially, the node feature as reliable information guidance is used to compute the underlying feature-oriented pair-wise node similarity, based on which the positive node pairs in contrastive regularizer are adjusted for better node representation characterization. According to the refined node representations, a triplet self-supervised clustering objective is well-designed to ensure the output embedding is cluster-oriented, and suitable for the downstream clustering task. Extensive experiments on seven benchmarks are conducted to demonstrate the effectiveness of HomoCAGC. © 1991-2012 IEEE.

关键词： Attributed graph clustering contrastive learning graph homophily self-supervised clustering

来源：评论

学校读者我要写书评

暂无评论

VBSSR: Variable Bitrate Encoded Video Streaming with Super-Resolution on HPC Education Platform 11th

VBSSR: Variable Bitrate Encoded Video Streaming with Super-R...

引用

11th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2020

作者： Wu, Run Zhou, Gangqiang Hu, Miao Wu, Di Department of Computer Science Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9789811600098

In online HPC education platforms, a large amount of educational resources are in the form of video. It is desirable to provide better QoE (Quality of Experience) for students when they are viewing these educational resources. Compared to traditional constant bitrate (CBR) encoding, variable bitrate (VBR) encoding can achieve better video quality and reduce network bandwidth. However, previous adaptive bitrate (ABR) schemes were commonly designed for CBR encoded videos. Such ABR schemes are not suitable to stream VBR encoded videos whose chunk sizes fluctuate rapidly. In this paper, we propose a novel ABR scheme call VBSSR, which takes the characteristics of VBR encoded video into consideration. The basic idea of VBSSR is to stream video chunks with complex scenes at a low bitrate level to reduce bandwidth consumption, and then boost the video quality by leveraging the technique of super-resolution (SR) at the client-side. VBSSR trains a deep reinforcement learning (DRL) based neural model to jointly make bitrate selections and decide which chunks to be enhanced. We conduct extensive trace-driven evaluations to compare VBSSR with other state-of-the-art methods. The experiment results show that our method significantly outperforms existing approaches with improvements in the average video quality by at least 37.1% while reducing the rebuffering time by 24.3%–75.9%. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

AMHF-TP: Multifunctional therapeutic peptides prediction based on multi-granularity hierarchical features

引用

Quantitative Biology 2025年第1期 44-58页

作者： Shouheng Tuo YanLing Zhu Jiangkun Lin Jiewei Jiang School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing School of Electronic Engineering Xi'an University of Posts and Telecommunications

Multifunctional therapeutic peptides(MFTP) hold immense potential in diverse therapeutic contexts, yet their prediction and identification remain challenging due to the limitations of traditional methodologies, such as extensive training durations, limited sample sizes, and inadequate generalization capabilities. To address these issues, we present AMHF-TP, an advanced method for MFTP recognition that utilizes attention mechanisms and multi-granularity hierarchical features to enhance performance. The AMHF-TP is composed of four key components: a migration learning module that leverages pretrained models to extract atomic compositional features of MFTP sequences; a convolutional neural network and selfattention module that refine feature extraction from amino acid sequences and their secondary structures; a hypergraph module that constructs a hypergraph for complex similarity representation between MFTP sequences; and a hierarchical feature extraction module that integrates multimodal peptide sequence features. Compared with leading methods,the proposed AMHF-TP demonstrates superior precision, accuracy, and coverage, underscoring its effectiveness and robustness in MFTP recognition. The comparative analysis of separate hierarchical models and the combined model, as well as with five contemporary models, reveals AMHF-TP's exceptional performance and stability in recognition tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge-Based Video Analytics: A Survey

arXiv

引用

arXiv 2023年

作者： Hu, Miao Luo, Zhenxiao Pasdar, Amirmohammad Lee, Young Choon Zhou, Yipeng Wu, Di School of Computer Science and Engineering The Guangdong Key Laboratory of Big Data Analysis and Processing Sun Yat-sen University China School of Computing Macquarie University Sydney Australia

Edge computing has been getting a momentum with ever-increasing data at the edge of the network. In particular, huge amounts of video data and their real-time processing requirements have been increasingly hindering the traditional cloud computing approach due to high bandwidth consumption and high latency. Edge computing in essence aims to overcome this hindrance by processing most video data making use of edge servers, such as small-scale on-premises server clusters, server-grade computing resources at mobile base stations and even mobile devices like smartphones and tablets;hence, the term edge-based video analytics. However, the actual realization of such analytics requires more than the simple, collective use of edge servers. In this paper, we survey state-of-the-art works on edge-based video analytics with respect to applications, architectures, techniques, resource management, security and privacy. We provide a comprehensive and detailed review on what works, what doesn't work and why. These findings give insights and suggestions for next generation edge-based video analytics. We also identify open issues and research directions. © 2023, CC BY.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Node Classification on Attributed Networks Based on Prototypical Network

Few-Shot Node Classification on Attributed Networks Based on...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yaliang Zhao Guangming Zhang Jinke Wang Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Henan University Kaifeng China

In today’s society, the interactions between various entities form complicated attributed networks. The node classification task as the core task of analyzing attribute networks has gained a considerable amount of attention from researchers. The existing graph neural network-based node classification approaches all demand lots of labeled data, but a high percentage of node classes in practical scenarios contain only restricted labeled data. So their classification effect is not good. In response to this problem, we put forward an improved graph prototypical network (IGPN) to enhance the few-shot node classification’s accuracy. In particular, we start by obtaining the embedding representations of nodes on the attributed network through a graph attention network. Then combined with the node’s degree information and neighbor information, the importance coefficient of all nodes in the support set is learned. After that, we can obtain the prototype representation of every class. Finally, the node classification can be completed by the distance of the query nodes’ representation from all class prototypes. Our method is preferable to the baseline method on three datasets according to a large number of experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimal location query based on k nearest neighbours

引用

Frontiers of Computer Science 2021年第2期15卷 105-117页

作者： Yubao LIU Zitong CHEN Ada Wai-Chee FU Raymond Chi-Wing WONG Genan DAI School of Data and Computer Science Sun Yat-Sen UniversityGuangzhou510006China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006China Department of Computer Science and Engineering Chinese University of Hong KongHong Kong999077China Department of Computer Science and Engineering The Hong Kong University of Science and TechnologyHong Kong999077China

Optimal location query in road networks is a basic operation in the location intelligence *** a set of clients and servers on a road network,the purpose of optimal location query is to obtain a location for a new server,so that a certain objective function calculated based on the locations of clients and servers is *** works assume no labels for servers and that a client only visits the nearest *** assumptions are not realistic and it renders the existing work not useful in many *** this paper,we relax these assumptions and consider the k nearest neighbours(KNN)of *** introduce the problem of KNN-based optimal location query(KOLQ)which considers the k nearest servers of clients and labeled *** also introduce a variant problem called relocation KOLQ(RKOLQ)which aims at relocating an existing server to an optimal *** main analysis algorithms are proposed for these *** experiments on the real road networks illustrate the efficiency of our proposed solutions.

关键词： optimal location query k nearest neighbours road network

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：