检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhong, Qihuang Li, Haiyun Zhuang, Luyao Liu, Juhua Du, Bo School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Aspect-based Sentiment Analysis (ABSA) is an important sentiment analysis task, which aims to determine the sentiment polarity towards an aspect in a sentence. Due to the expensive and limited labeled data, data generation (DG) has become the standard for improving the performance of ABSA. However, current DG methods usually have some shortcomings: 1) poor fluency and coherence, 2) lack of diversity of generated data, and 3) reliance on some existing labeled data, hindering its applications in real-world scenarios. With the advancement of large language models (LLMs), LLM-based DG has the potential to solve the above issues. Unfortunately, directly prompting LLMs struggles to generate the desired pseudo-label ABSA data, as LLMs are prone to hallucinations, leading to undesired data generation. To this end, we propose a systematic Iterative Data Generation framework, namely IDG, to boost the performance of ABSA. The core of IDG is to make full use of the powerful abilities (i.e., instruction-following, in-context learning and self-reflection) of LLMs to iteratively generate more fluent and diverse pseudo-label data, starting from an unsupervised sentence corpus. Specifically, IDG designs a novel iterative data generation mechanism and a self-reflection data filtering module to tackle the challenges of unexpected data generation caused by hallucinations. Extensive experiments on four widely-used ABSA benchmarks show that IDG brings consistent and significant performance gains among five baseline ABSA models. More encouragingly, the synthetic data generated by IDG can achieve comparable or even better performance against the manually annotated data. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedSSP: federated graph learning with spectral knowledge and personalized preference 24

FedSSP: federated graph learning with spectral knowledge and...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zihan Tan Guancheng Wan Wenke Huang Mang Ye National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China and Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

ISBN: (纸本)9798331314385

Personalized Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural Networks (GNNs) without compromising privacy while accommodating personalized requirements for non-IID participants. In cross-domain scenarios, structural heterogeneity poses significant challenges for pFGL. Nevertheless, previous pFGL methods incorrectly share non-generic knowledge globally and fail to tailor personalized solutions locally under domain structural shift. We innovatively reveal that the spectral nature of graphs can well reflect inherent domain structural shifts. Correspondingly, our method overcomes it by sharing generic spectral knowledge. Moreover, we indicate the biased message-passing schemes for graph structures and propose the personalized preference module. Combining both strategies, we propose our pFGL framework FedSSP which Shares generic Spectral knowledge while satisfying graph Preferences. Furthermore, We perform extensive experiments on cross-dataset and cross-domain settings to demonstrate the superiority of our framework. The code is available at https://***/OakleyTan/FedSSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parameter disparities dissection for backdoor defense in heterogeneous federated learning 24

Parameter disparities dissection for backdoor defense in het...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Wenke Huang Mang Ye Zekun Shi Guancheng Wan He Li Bo Du National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan University Wuhan China and Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

ISBN: (纸本)9798331314385

Backdoor attacks pose a serious threat to federated systems, where malicious clients optimize on the triggered distribution to mislead the global model towards a predefined target. Existing backdoor defense methods typically require either homogeneous assumption, validation datasets, or client optimization conflicts. In our work, we observe that benign heterogeneous distributions and malicious triggered distributions exhibit distinct parameter importance degrees. We introduce the Fisher Discrepancy Cluster and Rescale (FDCR) method, which utilizes Fisher Information to calculate the degree of parameter importance for local distributions. This allows us to reweight client parameter updates and identify those with large discrepancies as backdoor attackers. Furthermore, we prioritize rescaling important parameters to expedite adaptation to the target distribution, encouraging significant elements to contribute more while diminishing the influence of trivial ones. This approach enables FDCR to handle backdoor attacks in heterogeneous federated learning environments. Empirical results on various heterogeneous federated scenarios under backdoor attacks demonstrate the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Arbitrary Scale Super Resolution Network for Satellite Imagery

引用

China Communications 2022年第8期19卷 234-246页

作者： Jing Fang Jing Xiao Xu Wang Dan Chen Ruimin Hu National Engineering Research Center for Multimedia Software School of Computer ScienceWuhan UniversityWuhan 430072China Collaborative Innovation Center of Geospatial Technology Wuhan 430079China National University of Defense Technology Wuhan 430015China

Recently,satellite imagery has been widely applied in many ***,due to the limitations of hardware equipment and transmission bandwidth,the images received on the ground have low resolution and weak *** addition,since ground terminals have various resolutions and real-time playing requirements,it is essential to achieve arbitrary scale super-resolution(SR)of satellite *** this paper,we propose an arbitrary scale SR network for satellite image ***,we propose an arbitrary upscale module for satellite imagery that can map low-resolution satellite image features to arbitrary scale enlarged SR ***,we design an edge reinforcement module to enhance the highfrequency details in satellite images through a twobranch ***,extensive upsample experiments on WHU-RS19 and NWPU-RESISC45 datasets and subsequent image segmentation experiments both show the superiority of our method over the counterparts.

关键词： satellite imagery super resolution arbitrary upscale edge reinforcement video satellite

来源：评论

学校读者我要写书评

暂无评论

Dual-focus: person search from Coarse-Grained Focus to Fine-Grained Focus

Dual-focus: person search from Coarse-Grained Focus to Fine-...

引用

作者： Hu, Wenyi Wang, Xiao Wang, Zheng Xu, Xin Hu, Ruimin National Engineering Research Center for Multimedia Software Wuhan University Hubei Wuhan430079 China School of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China

Person search, which aims to find the target person in the whole scene images, has become a crucial application in security surveillance with various types of noise. Existing methods solve this problem by addressing two subtasks simultaneously: detection, distinguishing people from background noise;and identification, separating target from others noise. However, these two tasks are fundamentally contradictory, as detection is designed to be robust to intra-class variations to capture general human features, while identification is designed to be sensitive to inter-class variations to focus only on the target. Inspired by the observation that the police first narrowed the scope to a small group of people similar to the suspect, and then located the target, we propose a Dual-Focus framework consisting of Coarse-Grained Focus (search for similar people) and Fine-Grained Focus (find the target). Extensive experiments on datasets such as CUHK-SYSU and PRW are conducted to evaluate the effectiveness of our proposed methods. The evaluations demonstrate that our method delivers superior results compared with the state-of-art methods. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Coarse-Grained Focus Fine-Grained Focus Person search

来源：评论

学校读者我要写书评

暂无评论

A provable decision rule for out-of-distribution detection 24

A provable decision rule for out-of-distribution detection

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Xinsong Ma Xin Zou Weiwei Liu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

Out-of-distribution (OOD) detection task plays the key role in reliable and safety-critical applications. Existing researches mainly devote to designing or training the powerful score function but overlook investigating the decision rule based on the proposed score function. Different from previous work, this paper aims to design a decision rule with rigorous theoretical guarantee and well empirical performance. Specifically, we provide a new insight for the OOD detection task from a hypothesis testing perspective and propose a novel generalized Benjamini Hochberg (g-BH) procedure with empirical p-values to solve the testing problem. Theoretically, the g-BH procedure controls false discovery rate (FDR) at pre-specified level. Furthermore, we derive an upper bound of the expectation of false positive rate (FPR) for the g-BH procedure based on the tailed generalized Gaussian distribution family, indicating that the FPR of g-BH procedure converges to zero in probability. Finally, the extensive experimental results verify the superiority of g-BH procedure over the traditional threshold-based decision rule on several OOD detection benchmarks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Devil is in Details: Locality-Aware 3D Abdominal CT Volume Generation for Self-Supervised Organ Segmentation

arXiv

引用

arXiv 2024年

作者： Wang, Yuran Wan, Zhijing Qiu, Yansheng Wang, Zheng National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan University Wuhan China

In the realm of medical image analysis, self-supervised learning (SSL) techniques have emerged to alleviate labeling demands, while still facing the challenge of training data scarcity owing to escalating resource requirements and privacy constraints. Numerous efforts employ generative models to generate high-fidelity, unlabeled 3D volumes across diverse modalities and anatomical regions. However, the intricate and indistinguishable anatomical structures within the abdomen pose a unique challenge to abdominal CT volume generation compared to other anatomical regions. To address the overlooked challenge, we introduce the Locality-Aware Diffusion (Lad), a novel method tailored for exquisite 3D abdominal CT volume generation. We design a locality loss to refine crucial anatomical regions and devise a condition extractor to integrate abdominal priori into generation, thereby enabling the generation of large quantities of high-quality abdominal CT volumes essential for SSL tasks without the need for additional data such as labels or radiology reports. Volumes generated through our method demonstrate remarkable fidelity in reproducing abdominal structures, achieving a decrease in FID score from 0.0034 to 0.0002 on AbdomenCT-1K dataset, closely mirroring authentic data and surpassing current methods. Extensive experiments demonstrate the effectiveness of our method in self-supervised organ segmentation tasks, resulting in an improvement in mean Dice scores on two abdominal datasets effectively. These results underscore the potential of synthetic data to advance self-supervised learning in medical image analysis. Copyright © 2024, The Authors. All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

A theoretical analysis of backdoor poisoning attacks in convolutional neural networks 24

A theoretical analysis of backdoor poisoning attacks in conv...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Boqi Li Weiwei Liu School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China

The rising threat of backdoor poisoning attacks (BPAs) on Deep Neural Networks (DNNs) has become a significant concern in recent years. In such attacks, the adversaries strategically target a specific class and generate a poisoned training set. The neural network (NN), well-trained on the poisoned training set, is able to predict any input with the trigger pattern as the targeted label, while maintaining accurate outputs for clean inputs. However, why the BPAs work remains less explored. To fill this gap, we employ a dirty-label attack and conduct a detailed analysis of BPAs in a two-layer convolutional neural network. We provide theoretical insights and results on the effectiveness of BPAs. Our experimental results on two real-world datasets validate our theoretical findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-driven entropy aggregation for byzantine-robust heterogeneous federated learning 24

Self-driven entropy aggregation for byzantine-robust heterog...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Wenke Huang Zekun Shi Mang Ye He Li Bo Du National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China National Engineering Research Center for Multimedia Software School of Computer Science and Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

Federated learning presents massive potential for privacy-friendly collaboration. However, federated learning is deeply threatened by byzantine attacks, where malicious clients deliberately upload crafted vicious updates. While various robust aggregations have been proposed to defend against such attacks, they are subject to certain assumptions: homogeneous private data and related proxy datasets. To address these limitations, we propose Self-Driven Entropy Aggregation (SDEA), which leverages the random public dataset to conduct Byzantine-robust aggregation in heterogeneous federated learning. For Byzantine attackers, we observe that benign ones typically present more confident (sharper) predictions than evils on the public dataset. Thus, we highlight benign clients by introducing learnable aggregation weight to minimize the instanceprediction entropy of the global model on the random public dataset. Besides, with inherent data heterogeneity, we reveal that it brings heterogeneous sharpness. Specifically, clients are optimized under distinct distribution and thus present fruitful predictive preferences. The learnable aggregation weight blindly allocates high attention to limited ones for sharper predictions, resulting in a biased global model. To alleviate this problem, we encourage the global model to offer diverse predictions via batch-prediction entropy maximization and conduct clustering to equally divide honest weights to accommodate different tendencies. This endows SDEA to detect Byzantine attackers in heterogeneous federated learning. Empirical results demonstrate the effectiveness

关键词：

来源：评论

学校读者我要写书评

暂无评论

S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning 41

S3GCL: Spectral, Swift, Spatial Graph Contrastive Learning

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wan, Guancheng Tian, Yijun Huang, Wenke Chawla, Nitesh V. Ye, Mang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Department of Computer Science University of Notre Dame United States Taikang Center for Life and Medical Sciences Wuhan University Wuhan China

Graph Contrastive Learning (GCL) has emerged as a highly effective self-supervised approach in graph representation learning. However, prevailing GCL methods confront two primary challenges: 1) They predominantly operate under homophily assumptions, focusing on low-frequency signals in node features while neglecting heterophilic edges that connect nodes with dissimilar features. 2) Their reliance on neighborhood aggregation for inference leads to scalability challenges and hinders deployment in real-time applications. In this paper, we introduce S3GCL, an innovative framework designed to tackle these challenges. Inspired by spectral GNNs, we initially demonstrate the correlation between frequency and homophily levels. Then, we propose a novel cosine-parameterized Chebyshev polynomial as low/high-pass filters to generate biased graph views. To resolve the inference dilemma, we incorporate an MLP encoder and enhance its awareness of graph context by introducing structurally and semantically neighboring nodes as positive pairs in the spatial domain. Finally, we formulate a cross-pass GCL objective between full-pass MLP and biased-pass GNN filtered features, eliminating the need for augmentation. Extensive experiments on real-world tasks validate S3GCL proficiency in generalization to diverse homophily levels and its superior inference efficiency. Copyright 2024 by the author(s)

关键词： Contrastive Learning

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：