检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Peng, Sijia Xiong, Yun Zhu, Yangyong Shen, Zhiqiang Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Time series forecasting requires balancing short-term and long-term dependencies for accurate predictions. Existing methods mainly focus on long-term dependency modeling, neglecting the complexities of short-term dynamics, which may hinder performance. Transformers are superior in modeling long-term dependencies but are criticized for their quadratic computational cost. Mamba provides a near-linear alternative but is reported less effective in time series long-term forecasting due to potential information loss. Current architectures fall short in offering both high efficiency and strong performance for long-term dependency modeling. To address these challenges, we introduce Mixture of Universals (MoU), a versatile model to capture both short-term and long-term dependencies for enhancing performance in time series forecasting. MoU is composed of two novel designs: Mixture of Feature Extractors (MoF), an adaptive method designed to improve time series patch representations for short-term dependency, and Mixture of Architectures (MoA), which hierarchically integrates Mamba, FeedForward, Convolution, and Self-Attention architectures in a specialized order to model long-term dependency from a hybrid perspective. The proposed approach achieves state-of-the-art performance while maintaining relatively low computational costs. Extensive experiments on seven real-world datasets demonstrate the superiority of MoU. Code is available at https://***/lunaaa95/mou/. © 2024, CC BY.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Task Separation and Knowledge Sharing for Class Incremental Learning 5

Task Separation and Knowledge Sharing for Class Incremental ...

引用

5th International Conference on Intelligent Computing and Human-computer Interaction, ICHCI 2024

作者： Zhang, Jiali Qiao, Xiaoyan School of Computer Science and Technology Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China School of Mathematics and Information Science Shandong Technology and Business University Yantai Key Laboratory of Big Data Modeling and Intelligent Computing Immersion Technology and Evaluation Shandong Engineering Research Center Shandong Yantai China

ISBN: (纸本)9798350368284

Methods based on dynamically expanding architectures can effectively mitigate catastrophic forgetting in class incremental learning (CIL), but they often overlook information sharing and integration between subnetworks, leading to performance degradation and increased parameter count and memory consumption as the network expands. To address these complex issues, we introduce a new method called Task Separation and Knowledge Sharing (TSKS), which transfers knowledge at both the logical and feature levels through Hybrid Knowledge Distillation (HKD). In logical distillation, we combine Global Knowledge Distillation (GKD) and Task Knowledge Distillation (TKD) to establish connections between tasks. To prevent the model from favoring new classes, we design an Attention- Based Feature Fusion (ABFF) mechanism to capture important features. Additionally, we introduce a Soft-Margin Auxiliary Loss (SMAL) to help the model learn new concepts. Extensive experiments show that TSKS outperforms existing models on CIFAR100 and ImageNet100, regardless of whether memory samples are used. Notably, TSKS demonstrates superior performance in memory-free settings, indicating a reduced reliance on rehearsal memory. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base

arXiv

引用

arXiv 2023年

作者： Yuan, Siyu Chen, Jiangjie Sun, Changzhi Liang, Jiaqing Xiao, Yanghua Yang, Deqing School of Data Science Fudan University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China East China Normal University China

Analogical reasoning is a fundamental cognitive ability of humans. However, current language models (LMs) still struggle to achieve human-like performance in analogical reasoning tasks due to a lack of resources for model training. In this work, we address this gap by proposing ANALOGYKB, a million-scale analogy knowledge base (KB) derived from existing knowledge graphs (KGs). ANALOGYKB identifies two types of analogies from the KGs: 1) analogies of the same relations, which can be directly extracted from the KGs, and 2) analogies of analogous relations, which are identified with a selection and filtering pipeline enabled by large language models (LLMs), followed by minor human efforts for data quality control. Evaluations on a series of datasets of two analogical reasoning tasks (analogy recognition and generation) demonstrate that ANALOGYKB successfully enables both smaller LMs and LLMs to gain better analogical reasoning capabilities. Resources of this paper can be found at https://***/siyuyuan/ analogykb. © 2023, CC BY-NC-SA.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

DMNER: Biomedical Named Entity Recognition by Detection and Matching

DMNER: Biomedical Named Entity Recognition by Detection and ...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Bian, Junyi Jiang, Rongze Zhai, Weiqi Huang, Tianyang Huang, Xiaodi Zhou, Hong Zhu, Shanfeng Fudan University School of Computer Science Shanghai China Fudan University Institute of Science and Technology for Brain-Inspired Intelligence Shanghai China Charles Sturt University School of Computing Mathematics and Engineering Nsw Australia Atypon Systems Llc United Kingdom Zhangjiang Fudan International Innovation Center Fudan University Institute of Science and Technology for Brain-Inspired Intelligence Moe Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Shanghai China

ISBN: (纸本)9798350386226

Biomedical Named Entity Recognition (NER) is a crucial task in extracting information from biomedical texts. However, the diversity of professional terminology, semantic complexity, and the widespread presence of synonyms pose significant challenges. Traditional methods that rely on sequence labeling training datasets often struggle to handle these complexities. To address this, we introduce a novel framework for BioNER, termed DMNER, which leverages external knowledge and operates in two steps: entity boundary detection and entity category identification through matching. The core of DMNER is its second step, which determines the entity category by retrieving similar entities and their categories from a knowledge dictionary using semantic similarity matching. Our experiments on 10 biomedical datasets demonstrate that DMNER outperforms baselines across these tasks, proving its effectiveness and adaptability. DMNER is versatile and can be applied to various NER tasks, including supervised NER, distantly supervised NER, and NER on multiple datasets with disjoint label sets. The DMNER code is publicly available. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Note on a New Construction of Kantorovich Form q-Bernstein Operators Related to Shape Parameter λ

引用

computer Modeling in Engineering & sciences 2022年第3期130卷 1479-1493页

作者： Qingbo Cai Resat Aslan Fujian Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information ProcessingSchool of Mathematics and Computer ScienceQuanzhou Normal UniversityQuanzhou362000China Department of Mathematics Faculty of Sciences and ArtsHarran UniversitySanlıurfa63300Turkey

The main purpose of this paper is to introduce some approximation properties of a Kantorovich kind q-Bernstein operators related to B′ezier basis functions with shape parameterλ∈[−1,1].Firstly,we compute some basic results such as moments and central moments,and derive the Korovkin type approximation theorem for these ***,we estimate the order of convergence in terms of the usual modulus of continuity,for the functions belong to Lipschitz-type class and Peetre’s K-functional,***,with the aid of Maple software,we present the comparison of the convergence of these newly defined operators to the certain function with some graphical illustrations and error estimation table.

关键词： q-calculus (λ,q)-Bernstein polynomials order of convergence Lipschitz-type function Peetre’s K-functional

来源：评论

学校读者我要写书评

暂无评论

Improving the second-tier classification of methylmalonic acidemia patients using a machine learning ensemble method

引用

World Journal of Pediatrics 2024年第10期20卷 1090-1101页

作者： Zhi-Xing Zhu Georgi ZGenchev Yan-Min Wang Wei Ji Yong-Yong Ren Guo-Li Tian Sira Sriswasdi Hui Lu Shanghai Engineering Research Center for Big Datain Pediatric Precision Medicine Center for BiomedicalInformaticsShanghai Children’s HospitalSchoolof MedicineShanghai Jiao Tong UniversityShanghaiChina Center of Excellence in Computational Molecular Biology Faculty of MedicineChulalongkorn UniversityBangkokThailand Newborn Screening Center Shanghai Children’s HospitalSchool of MedicineShanghai Jiao Tong UniversityShanghaiChina SJTU-Yale Joint Center for Biostatistics and Data Science National Center for Translational MedicineShanghai JiaoTong UniversityShanghaiChina Center for Artifcial Intelligence in Medicine ResearchAfairsFaculty of MedicineChulalongkorn UniversityBangkokThailand State Key Laboratory of Microbial Metabolism JointInternational Research Laboratory of Metabolic&Developmental SciencesDepartment of Bioinformaticsand BiostatisticsSchool of Life Sciences and BiotechnologyShanghai Jiao Tong UniversityShanghaiChina

Introduction Methylmalonic acidemia(MMA)is a disorder of autosomal recessive inheritance,with an estimated prevalence of 1:50,***-tier clinical diagnostic tests often return many false positives[fve false positive(FP):one true positive(TP)].In this work,our goal was to refne a classifcation model that can minimize the number of false positives,currently an unmet need in the upstream diagnostics of *** We developed machine learning multivariable screening models for MMA with utility as a secondary-tier tool for false positives *** utilized mass spectrometry-based features consisting of 11 amino acids and 31 carnitines derived from dried blood samples of neonatal patients,followed by additional ratio feature *** selection strategies(selection by flter,recursive feature elimination,and learned vector quantization)were used to determine the input set for evaluating the performance of 14 classifcation models to identify a candidate model set for an ensemble model *** Our work identifed computational models that explore metabolic analytes to reduce the number of false positives without compromising *** best results[area under the receiver operating characteristic curve(AUROC)of 97%,sensitivity of 92%,and specifcity of 95%]were obtained utilizing an ensemble of the algorithms random forest,C5.0,sparse linear discriminant analysis,and autoencoder deep neural network stacked with the algorithm stochastic gradient boosting as the *** model achieved a good performance trade-of for a screening application with 6%false-positive rate(FPR)at 95%sensitivity,35%FPR at 99%sensitivity,and 39%FPR at 100%*** The classifcation results and approach of this research can be utilized by clinicians globally,to improve the overall discovery of MMA in pediatric *** improved method,when adjusted to 100%precision,can be used to further inform the diagnostic process journey of MMA and help r

关键词： Machine learning Methylmalonic acidemia Second-tier test Stacking

来源：评论

学校读者我要写书评

暂无评论

AutoConsis: Automatic GUI-driven data Inconsistency Detection of Mobile Apps

AutoConsis: Automatic GUI-driven Data Inconsistency Detectio...

引用

IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice Track (ICSE-SEIP)

作者： Yongxiang Hu Hailiang Jin Xuan Wang Tiazhen Gu Shiyu Guo Chaoyi Chen Xin Wang Yangfan Zhou School of Computer Science Fudan University Shanghai China Meituan Shanghai China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China

ISBN: (数字)9798400705014

ISBN: (纸本)9798350352177

In industrial practice, many bugs in commercial mobile apps manifest as self-conflicts of data presented in the GUI (Graphical User Interface). Such data inconsistency bugs can bring confusion to the users and deteriorate user experiences. They are a major target of industrial testing practice. However, due to the complication and diversity of GUI implementation and data presentation (e.g., the ways to present the data in natural language), detecting data inconsistency bugs is a very challenging task. It still largely relies on manual efforts. To reduce such human efforts, we proposed Au-toConsis, an automated data inconsistency testing tool we designed for Meituan. one of the largest E-commerce providers with over 600 million transacting users. AutoConsis can automatically analyze GUI pages via a multi-modal deep-learning model and extract target data from textual phrases leveraging LLMs (Large Language Models). With these extracted data, their inconsistencies can then be detected. We evaluate the design of AutoConsis via a set of ablation experiments. Moreover, we demonstrate the effectiveness of AutoConsis when applying it to real-world commercial mobile apps with eight representative cases.

关键词： Target recognition computer bugs data models Software Mobile applications data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Gradient-free methods for nonconvex nonsmooth stochastic compositional optimization 24

Gradient-free methods for nonconvex nonsmooth stochastic com...

引用

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

作者： Zhuanghua Liu Luo Luo Bryan Kian Hsiang Low Department of Computer Science National University of Singapore CNRS@CREATE LTD Singapore School of Data Science Fudan University Shanghai Key Laboratory for Contemporary Applied Mathematics Department of Computer Science National University of Singapore

ISBN: (纸本)9798331314385

Stochastic compositional optimization (SCO) problems are popular in many real-world applications, including risk management, reinforcement learning, and meta-learning. However, most of the previous methods for SCO require the smoothness assumption on both the outer and inner functions, which limits their applications to a wider range of problems. In this paper, we study the SCO problem in that both the outer and inner functions are Lipschitz continuous but possibly nonconvex and nonsmooth. In particular, we propose gradient-free stochastic methods for finding the (δ, ε)-Goldstein stationary points of such problems with non-asymptotic convergence rates. Our results also lead to an improved convergence rate for the convex nonsmooth SCO problem. Furthermore, we conduct numerical experiments to demonstrate the effectiveness of the proposed methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CoCGAN: Contrastive Learning for Adversarial Category Text Generation 29

CoCGAN: Contrastive Learning for Adversarial Category Text G...

引用

29th International Conference on Computational Linguistics, COLING 2022

作者： Sheng, Xin Xu, Linli Xu, Yinlong Bao, Changcun Chen, Huang Ren, Bo Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence China Tencent Youtu Lab China

The task of generating texts of different categories has attracted more and more attention in the area of natural language generation recently. Meanwhile, generative adversarial net (GAN) has demonstrated its effectiveness on text generation, and is further applied to category text generation in later works. Different from existing methods, which mainly consider the pairwise relations between the text embedding and the corresponding fixed one-hot class label (data-to-class relations), this paper proposes a novel Contrastive Category Generative Adversarial Net (CoCGAN) to incorporate contrastive learning into adversarial category text generation, considering more flexible data-to-class relations as well as relations between the multiple text embeddings in the same batch (data-to-data relations). The discriminator of CoCGAN discriminates the authenticity of given samples and optimizes a contrastive learning objective to capture both more flexible data-to-class relations and data-to-data relations among training samples. Accordingly, the generator tries to produce more realistic samples which can confuse the discriminator. Experimental results on both synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generation models. © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Why was Pakistan extreme precipitation stronger in 2022 than in 2010?

引用

Advances in Climate Change Research 2023年第6期14卷 913-920页

作者： Xu YUAN Kun YANG Jing SUN Yan WANG Yan-Yi HE Mi-Jun ZOU Yao-Zhi JIANG Polar and Marine Research Institute College of Harbor and Coastal EngineeringJimei UniversityXiamen 361021China Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System ScienceTsinghua UniversityBeijing 100084China National Tibetan Plateau Data Center State Key Laboratory of Tibetan Plateau Earth SystemResource and EnvironmentChinese Academy of SciencesBeijing 100101China Institue of Geographic Science and Natural Resources Research Chinese Academy of Sciences Beijing 100101China School of Environmental and Geographical Science Shanghai Normal UniversityShanghai 200234China Yangtze River Delta National Observatory of Wetland Ecosystem Shanghai Normal UniversityShanghai 200234China

In Pakistan,five continuous extreme precipitation events in the summer(July-August)of 2022 caused disastrous floods,depriving thousands of people's lives and ruining millions of *** tremendous disaster in Pakistan also happened in 2010 but with three concentrated extreme precipitation events in the middle of *** amount of Pakistan heavy daily precipitation in 2022 surpasses that in 2010 record,making it the strongest precipitation event ever *** comprehensively understand the causes of extreme precipitation in Pakistan,this study investigated the anomalies in atmospheric circulation and moisture contribution of 2010/2022 extreme precipitation and compared their *** results show that an atmospheric blocking over northern Europe in both 2022 and 2010 enhanced convection in Pakistan by transporting cold-dry air from the high-latitude region and benefiting warm-wet monsoonal air marching to *** employing a moisture track model,the main moisture sources for summer precipitation in Pakistan were *** is found that moisture contributions except from Eurasia were enhanced,causing extreme *** particular,enhanced moisture contribution from the southern Indian Ocean and the northern Indian continent in 2022 are more prominent than that in *** increased moisture contribution in 2010 was due to increased evaporation induced by warming sea surface in the Indian Ocean,while much richer moisture transport in 2022 was attributed to the enhanced cross-equatorial flow induced by the anomalous subtropical high in the Southern ***,attention should be paid to the role of subtropical high in the Southern Hemisphere in addition to those in Northern Hemisphere in understanding disastrous extreme precipitation events inPakistan.

关键词： Extreme precipitation Moisture transport Moisture sources Pakistan

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：