检索结果-内蒙古大学图书馆

6th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2023

作者： Sun, Dazhi Yu, Canping Li, Li Li, Yingsong Xiao, Wudang Chen, Yong Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China Aircraft Airworthiness Institute China Academy of Civil Aviation Science and Technology Center of Aviation Safety Technology Cast Beijing101399 China

ISBN: (纸本)9798350399059

In practical applications, noise is more appropriately modelled as an a-stable random process than as a Gaussian process. To cope with a-stable noise, a fractional-order stochastic gradient descent (SGD) method is invented to adaptive filtering (AF) algorithms. When both input signal and noise follow α-stable random processes, the AF algorithms based on mean square error (MSE) criteria can be affected. Nevertheless, the fractional-order AF (FoAF) algorithm can effectively address this issue. For the purpose of better stability performance of the FoAF algorithm, different cost functions (CFs) are introduced into fractional-order SGD method. Based on the fractional-order derivative of a logarithmic CF (LCF), a fractional-order logarithmic adaptive filtering (FoLAF) algorithm is formed in this condition. Trials show that the FoLAF algorithm achieves faster convergence, excellent steady-state performance and superior tracking performance. © 2023 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models

arXiv

引用

arXiv 2024年

作者： Yang, Wenxuan Tan, Weimin Sun, Yuqi Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models. This involves strategies that focus on data quality rather than quantity, ensuring the data used for training has high informational value. Data-effective learning plays a profound role in accelerating foundation model training, reducing computational costs, and saving data storage, which is very important as the volume of medical data in recent years has grown beyond many people's expectations. However, due to the lack of standards and comprehensive benchmark, research on medical data-effective learning is poorly studied. To address this gap, our paper introduces a comprehensive benchmark specifically for evaluating data-effective learning in the medical field. This benchmark includes a dataset with millions of data samples from 31 medical centers (DataDEL), a baseline method for comparison (MedDEL), and a new evaluation metric (NormDEL) to objectively measure data-effective learning performance. Our extensive experimental results show the baseline MedDEL can achieve performance comparable to the original large dataset with only 5% of the data. Establishing such an open data-effective learning benchmark is crucial for the medical foundation model research community because it facilitates efficient data use, promotes collaborative breakthroughs, and fosters the development of cost-effective, scalable, and impactful healthcare solutions. The benchmark can be accessed at GitHub Repository. Copyright © 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

Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement

arXiv

引用

arXiv 2024年

作者： Huang, Zisu Wang, Xiaohua Zhang, Feiran Xu, Zhibo Zhang, Cenyuan Qian, Qi Zheng, Xiaoqing Huang, Xuanjing School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai China

The capacity of large language models (LLMs) to generate honest, harmless, and helpful responses heavily relies on the quality of user prompts. However, these prompts often tend to be brief and vague, thereby significantly limiting the full potential of LLMs. Moreover, harmful prompts can be meticulously crafted and manipulated by adversaries to jailbreak LLMs, inducing them to produce potentially toxic content. To enhance the capabilities of LLMs while maintaining strong robustness against harmful jailbreak inputs, this study proposes a transferable and pluggable framework that refines user prompts before they are input into LLMs. This strategy improves the quality of the queries, empowering LLMs to generate more truthful, benign and useful responses. Specifically, a lightweight query refinement model is introduced and trained using a specially designed reinforcement learning approach that incorporates multiple objectives to enhance particular capabilities of LLMs. Extensive experiments demonstrate that the refinement model not only improves the quality of responses but also strengthens their robustness against "jailbreak" attacks. © 2024, CC BY.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

IF-Font: Ideographic Description Sequence-Following Font Generation 38

IF-Font: Ideographic Description Sequence-Following Font Gen...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Chen, Xinping Ke, Xiao Guo, Wenzhong Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou350116 China

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at https://***/Stareven233/IF-Font. © 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

Unifying Dual-Space Embedding for Entity Alignment via Contrastive Learning 31

Unifying Dual-Space Embedding for Entity Alignment via Contr...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Cunda Wang, Weihua Liang, Qiuyu Bao, Feilong Gao, Guanglai College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (纸本)9798891761964

Entity alignment (EA) aims to match identical entities across different knowledge graphs (KGs). Graph neural network-based entity alignment methods have achieved promising results in Euclidean space. However, KGs often contain complex local and hierarchical structures, which are hard to represent in a single space. In this paper, we propose a novel method named as UniEA, which unifies dual-space embedding to preserve the intrinsic structure of KGs. Specifically, we simultaneously learn graph structure embeddings in both Euclidean and hyperbolic spaces to maximize the consistency between embeddings in the two spaces. Moreover, we employ contrastive learning to mitigate the misalignment issues caused by similar entities, where embeddings of similar neighboring entities become too close. Extensive experiments on benchmark datasets demonstrate that our method achieves state-of-the-art performance in structure-based EA methods. Our code is available at https://***/wonderCS1213/UniEA. © 2025 Association for Computational Linguistics.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

intelligent Logistics Service Quality Assurance Mechanism Based on Federated Collaborative Cache in 5G+ Edge Computing Environment 16th

Intelligent Logistics Service Quality Assurance Mechanism Ba...

引用

16th EAI International Conference on Wireless Internet, WiCON 2023

作者： Liu, Yiwen Fu, Jinrong Zhao, Zikai Yang, Yahui Peng, Ling Qu, Taiguo Feng, Tao School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Huaihua418000 China School of Foreign Languages Huaihua University Huaihua418000 China

ISBN: (纸本)9783031580529

Aiming at the problem of quality assurance of intelligent logistics service in 5G+ edge computing environment, this paper proposes a mechanism based on federated cooperative cache, which aims to utilize the computing and storage resources of edge nodes to realize rapid processing and sharing of logistics data and improve the efficiency and reliability of logistics services. This paper first analyzes the characteristics and challenges of intelligent logistics services under 5G+ edge computing environment, and then introduces the concept and principle of federated cooperative cache, as well as its application scenarios and advantages in intelligent logistics services. Then, this paper designs an intelligent logistics service quality assurance mechanism based on federated cooperative cache, including five modules such as data partitioning, data transmission, data fusion, data access and data update, and gives the corresponding algorithms and processes. Finally, this paper verifies the effectiveness and performance of the proposed mechanism through simulation experiments. Compared with the traditional centralized cache and distributed cache, the proposed mechanism can reduce the data transmission delay, improve the data hit rate and data consistency, so as to ensure the quality of intelligent logistics services. In the future, the federated collaborative cache mechanism can be further optimized to consider the needs of multiple scenarios. And explore the application potential of other areas to drive the continuous development and innovation of intelligent logistics services. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

An end-to-end algorithm for predicting missing load data based on waveGAIN

An end-to-end algorithm for predicting missing load data bas...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jiang Zhang Gang Zhou Yuwei Feng Sen Yang Wanlin Wang Jiaqing Mo Xinjiang Key Laboratory of Signal Detection and Processing School of Computer Science and Technology Xinjiang University Urumqi China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The accuracy of short-term load forecasting has improved with the development of deep learning on complete datasets. However, load data is often lost due to various complex factors in the power system, causing it is a challenge for incomplete load forecasting. To address this issue, this paper proposes an end-to-end load-completion and forecasting network. Specially, we designed the Wavelet-enhanced Generative Adversarial Imputation Net (waveGAIN) to improve the accuracy of data completion. Then, we propose an end-to-end training strategy that combines waveGAIN and Bidirectional Long Short-Term Memory (BiLSTM) networks to improve the accuracy of data filling and reduce the load forecasting error. The experimental results show that our proposed method improves the prediction accuracy in the case of different patterns and levels of missing data. And our method achieves good results even in case of 80% missing data.

关键词： Training Deep learning Accuracy Load forecasting Predictive models Data models Power systems

来源：评论

学校读者我要写书评

暂无评论

2023 7th International Conference on Communication and Information Systems An Improved IOTA Protocol Based on Optimal Midway Walk 7

2023 7th International Conference on Communication and Infor...

引用

7th International Conference on Communication and Information Systems, ICCIS 2023

作者： Wu, Hongcheng Zhi, Hui Liu, Yangyang Anhui University School of Electronic and Information Engineering Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei230601 China Hefei Zhilian Technology Industry Investment Co. Ltd Hefei230601 China

ISBN: (纸本)9798350330540

IOTA (Internet of Things Applications) protocol aims to provide a secure and trustworthy protocol for realizing data-value interactions between IoT devices, and it has become the next possible direction for the development of Blockchain applications. IOTA protocol has the problem that the time-consuming cumulative weight update grows too fast with the increase of the number of transactions, this paper proposed an improved IOTA protocol based on optimal midway walk, the improved protocol uses cutting-edge transaction selection algorithm of weighted Monte Carlo Markov random walk to reduce cumulative weight update delay. Firstly, this improved IOTA protocol mainly ensures the efficiency of transaction confirmation without losing the security of consensus by introducing the optimal midway walk method, i.e., the starting point of each walk is chosen to depart at an optimal location. Secondly, this paper designs the indirect verification identity record algorithm and the layer degree of confirmation principle are designed to realize the improved IOTA protocol's resilience and resistance to Parasite chain attack. The experimental results show that the improved IOTA using random function to select the midway walk starting point from i-50λ, to i-75λsubstantially solves the system computational burden problem and greatly reduces the cumulative weight update delay. © 2023 IEEE.

关键词： cumulative weight IOTA midway walk Parasite chain attack

来源：评论

学校读者我要写书评

暂无评论

Buffered Gaussian Modeling for Vectorized HD Map Construction

Buffered Gaussian Modeling for Vectorized HD Map Constructio...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Anqi Shi Huaqiu Chen Hong Lu Rui Zhang Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

Vectorized high-definition (HD) map construction is an important and challenging task for autonomous driving. End-to-end models have been developed recently to enable online map construction. Existing works have difficulty on generating complex geometric shapes and lack comprehensive evaluation metrics. To tackle these challenges, we introduce buffered IoU as a novel metric for vectorized map construction, which is clearly defined and applicable to real-world situations. Inspired by methods of rotated object detection, we further propose a novel technique called Buffered Gaussian Modeling. We extend 1D line segments into 2D Gaussian distributions, making them easier to learn. With Gaussian-based losses, map elements are learned by their geometric features rather than coordinates only. Experiments performed on nuScenes dataset show that our method significantly improves the quality of map generation, using both distance-based and IoU-based metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Facial Micro-Motion-Aware Mixup for Micro-Expression Recognition

Facial Micro-Motion-Aware Mixup for Micro-Expression Recogni...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Zhuoyao Gu Miao Pang Zhen Xing Weimin Tan Xuhao Jiang Bo Yan School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai China

Data-driven learning models have demonstrated strong benefits in capturing subtle facial movements for micro-expression recognition (MER), but are limited by the available data. Generative models can generate a variety of new data, but are typically computationally prohibitive compared to efficient Mixup-like methods. In this paper, we propose a novel Facial Micro-Motion-Aware Mixup approach for MER, namely MEMix. Our MEMix constructs a micro-motion-aware mask to select the most salient facial motions and generate a new sample with a mixed motion feature. This mixed motion feature can effectively expand the data distribution, leading to smoother decision boundaries for MER models. To demonstrate the good generality of MEMix, we integrate it with three advanced vision transformer-based models. The results show that the three integrated models consistently achieve performance improvements ranging from 4.07% to 7.32% in accuracy and from 6.54% to 9.18% in F1-score. Besides, to further explore the ability of MEMix, we propose a two-stream network called MixMeFormer, which unlocks the potential of the transformer by simply integrating mixed motion features with facial semantics for MER. Extensive experiments demonstrate that our MixMeFormer outperforms other state-of-the-art methods on three well-known micro-expression datasets.

关键词：

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：