检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Hu, Jiacong Gao, Jing Ye, Jingwen Gao, Yang Wang, Xingen Feng, Zunlei Song, Mingli College of Computer Science and Technology Zhejiang University China Robotics Institute School of Computer Science Carnegie Mellon University United States Electrical and Computer Engineering National University of Singapore Singapore School of Software Technology Zhejiang University China State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China Bangsheng Technology Co. Ltd. China

With the rapid development of deep learning, the increasing complexity and scale of parameters make training a new model increasingly resource-intensive. In this paper, we start from the classic convolutional neural network (CNN) and explore a paradigm that does not require training to obtain new models. Similar to the birth of CNN inspired by receptive fields in the biological visual system, we draw inspiration from the information subsystem pathways in the biological visual system and propose Model Disassembling and Assembling (MDA). During model disassembling, we introduce the concept of relative contribution and propose a component locating technique to extract task-aware components from trained CNN classifiers. For model assembling, we present the alignment padding strategy and parameter scaling strategy to construct a new model tailored for a specific task, utilizing the disassembled task-aware components. The entire process is akin to playing with LEGO bricks, enabling arbitrary assembly of new models, and providing a novel perspective for model creation and reuse. Extensive experiments showcase that task-aware components disassembled from CNN classifiers or new models assembled using these components closely match or even surpass the performance of the baseline, demonstrating its promising results for model reuse. Furthermore, MDA exhibits diverse potential applications, with comprehensive experiments exploring model decision route analysis, model compression, knowledge distillation, and more. For more information, please visit https://***/. © 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

A Congestion Control Algorithm for Live Video Streaming in Dynamic Network 11

A Congestion Control Algorithm for Live Video Streaming in D...

引用

11th IEEE International Conference on Cyber Security and Cloud Computing, CSCloud 2024

作者： Pan, Wenqi Tan, Bin Hu, Die Wu, Jun College of Electronic and Information Engineering Tongji University Shanghai China College of Electronic and Information Engineering Jinggangshan University Jian China Fudan University Key Laboratory of EMW Information Shanghai China School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798350376982

Traditional TCP has been the dominant protocol for internet traffic after years of development in both academia and industry. However, the emergence of live video streaming applications and the increasing demand for low-latency video transmission, particularly in the context of sports and game live streaming, has posed a challenge to traditional TCP congestion control algorithms. As a representative TCP algorithm, BBR has been widely used in industry. However, BBR tends to inject more packets than the actual bottleneck in the dynamic network resulting in high latency. Because the maximum bandwidth in the past period is used to calculate the congestion window (CWND). To address this issue, we develop a recursive least squares (RLS) model to predict future bandwidth based on past bandwidth samples and update BBR's CWND periodically. To overcome the difficulty of modifying the kernel congestion control algorithm, we use extended Berkeley Packet Filter (eBPF) technology to rewrite TCP BBR and use eBPF MAP to exchange data between the kernel space and the data space. Experiments show that our algorithm can effectively reduce latency for live streaming in the dynamic network. Compared with CUBIC, our algorithm can achieve 76.9% average latency reduction with 2.3% average throughput loss and bring 42.4% average latency reduction with 1.9% average throughput loss compared with BBR. © 2024 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Symptom Dimensions and Cognitive Impairments in Individuals at Clinical High Risk for Psychosis

引用

Biological Psychiatry: Cognitive Neuroscience and Neuroimaging 2025年第6期10卷 646-655页

作者： Zhang, TianHong Xu, LiHua Wei, YanYan Cui, HuiRu Tang, XiaoChen Hu, YeGang Liu, HaiChun Wang, ZiXuan Chen, Tao Yi, ZhengHui Li, ChunBo Wang, JiJun Shanghai Mental Health Center Shanghai Jiaotong University School of Medicine Shanghai Engineering Research Center of Intelligent Psychological Evaluation and Intervention Shanghai Key Laboratory of Psychotic Disorders Shanghai China Department of Automation Shanghai Jiao Tong University Shanghai China Department of Psychology Shanghai Xinlianxin Psychological Counseling Center Shanghai China Big Data Research Laboratory University of Waterloo Waterloo ON Canada Labor and Worklife Program Harvard University Cambridge Massachusetts United States Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Institute of Psychology and Behavioral Science Shanghai Jiao Tong University Shanghai China

Background: Understanding the intricate relationships between symptom dimensions, clusters, and cognitive impairments is crucial for early detection and intervention in individuals at clinical high risk for psychosis. This study delves into this complex interplay in a clinical high risk sample with the aim of predicting the conversion to psychosis. Methods: A comprehensive cognitive assessment was performed in 744 clinical high risk individuals. The study included a 3-year follow-up period to allow assessment of conversion to psychosis. Symptom profiles were determined using the Structured Interview for Prodromal Syndromes. By applying factor analysis, symptom dimensions were categorized as dominant negative symptoms (NS), positive symptoms-stressful, and positive symptoms-odd. The factor scores were used to define 3 dominant symptom groups. Latent class analysis (LCA) and the factor mixture model (FMM) were employed to identify discrete clusters based on symptom patterns. The 3-class solution was chosen for the LCA and FMM analysis. Results: Individuals in the dominant NS group exhibited significantly higher conversion rates to psychosis than those in the other groups. Specific cognitive variables, including performance on the Brief Visuospatial Memory Test–Revised (odds ratio = 0.702, p = .001) and Neuropsychological Assessment Battery Mazes Test (odds ratio = 0.776, p = .024), significantly predicted conversion to psychosis. Notably, cognitive impairments associated with NS and positive symptoms-stressful groups affected different cognitive domains. LCA and FMM cluster 1, which was characterized by severe NS and positive symptoms-odd, exhibited more impairments in cognitive domains than other clusters. No significant difference in the conversion rate was observed among the LCA and FMM clusters. Conclusions: These findings highlight the importance of NS in the development of psychosis and suggest specific cognitive domains that are affected by symptom dimensions.

关键词： Negative symptoms Neurocognition Subtype Transition Ultra high risk

来源：评论

学校读者我要写书评

暂无评论

C2BERT: Cross-contrast BERT for Chinese Biomedical Sentence Representation

C2BERT: Cross-contrast BERT for Chinese Biomedical Sentence ...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Wang, Xiaosu Xiong, Yun Niu, Hao Zhang, Yao Zhu, Yangyong Fudan University Shanghai Key Laboratory of Data Science School of Computer Science China Shanghai Institute for Advanced Communication and Data Science Fudan University China

ISBN: (纸本)9781665401265

Pre-trained language models (PLMs), such as BERT, have achieved great success on various natural language processing (NLP) tasks. Nevertheless, we observe that PLM-derived native Chinese biomedical sentence representations are somehow collapsed, which means PLMs induce a non-smooth anisotropic semantic space of Chinese biomedical sentences and most sentences are mapped into a small area and therefore produce high similarity. Such PLM-derived native sentence representations poorly capture semantic meaning of Chinese biomedical *** alleviate the aforementioned collapse issue, we then propose a novel contrastive learning framework, named Cross-contrast BERT (C2 BERT), that advances the state-of-the-art Chinese biomedical sentence embeddings. C2 BERT proposes to derive positive/negative samples from two transformer-based different PLMs;this design decision reflects our philosophy that our goal is to conflate the knowledge stored in different PLMs to produce Chinese biomedical sentence embeddings, rather than introducing new noise. Moreover, without costly further pretraining, C2 BERT exploits contrastive learning as an auxiliary training objective during fine-tuning with supervision from biomedical sentence-related tasks. We demonstrate with extensive experiments that our C2 BERT model is more effective than competitive baselines on diverse Chinese biomedical sentence-related tasks. © 2021 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Detecting DTI Using Graph Embedding and Multi-Head Attention Mechanism

Detecting DTI Using Graph Embedding and Multi-Head Attention...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xiaoli Chen, Yaoyu Yang, Wenli Yu, HaiPing Wu, Zimo Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan China China Graphics Society School of Information Wuhan Vocational College Professional Committee of Graphics and Big Data Wuhan China

ISBN: (纸本)9798350386226

Drug-target interaction (DTI) prediction has an important role in drug discovery, significantly expediting the drug design and development process. This paper proposes a new model, ERW-BiAN, that seamlessly integrates graph embedding representations with deep learning network. Specifically, we utilize an improved graph embedding model, ERW, to generate comprehensive feature vectors for each node within the knowledge graph. Subsequently, these feature vectors are fed into the BiAN model, which leverages an attention mechanism to assign precise weights to sequences. Experimental results demonstrate the superior accuracy and predictive prowess of ERW-BiAN in DTI prediction tasks. Furthermore, the case about COVID-19 shows that ERW-BiAN has the better application potential for predicting drug-target interactions. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Integrating multi-omics data of childhood asthma using a deep association model

引用

Fundamental Research 2024年第4期4卷 738-751页

作者： Kai Wei Fang Qian Yixue Lia Tao Zeng Tao Huang Bio-Med Big Data Center CAS Key Laboratory of Computational BiologyShanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesChinese Academy of SciencesShanghai 200031China Guoke Ningbo Life Science and Health Industry Research Institute Ningbo 315000China Guangzhou National Laboratory Guangzhou 510000China GMU-GIBH Joint School of Life Sciences The Guangdong-Hong Kong-Macao Joint Laboratory for Cell Fate Regulation and DiseasesGuangzhou LaboratoryGuangzhou Medical UniversityGuangzhou 510000China Key Laboratory of Systems Health Science of Zhejiang Province School of Life ScienceHangzhou Institute for Advanced StudyUniversity of Chinese Academy of SciencesHangzhou 310024China

Childhood asthma is one of the most common respiratory diseases with rising mortality and *** multi-omics data is providing a new chance to explore collaborative biomarkers and corresponding diagnostic models of childhood *** capture the nonlinear association of multi-omics data and improve interpretability of diagnostic model,we proposed a novel deep association model(DAM)and corresponding efficient analysis ***,the Deep Subspace Reconstruction was used to fuse the omics data and diagnostic information,thereby correcting the distribution of the original omics data and reducing the influence of unnecessary data ***,the Joint Deep Semi-Negative Matrix Factorization was applied to identify different latent sample patterns and extract biomarkers from different omics data ***,our newly proposed Deep Orthogonal Canonical Correlation Analysis can rank features in the collaborative module,which are able to construct the diagnostic model considering nonlinear correlation between different omics data *** DAM,we deeply analyzed the transcriptome and methylation data of childhood *** effectiveness of DAM is verified from the perspectives of algorithm performance and biological significance on the independent test dataset,by ablation experiment and comparison with many baseline methods from clinical and biological *** DAM-induced diagnostic model can achieve a prediction AUC of o.912,which is higher than that of many other alternative ***,relevant pathways and biomarkers of childhood asthma are also recognized to be collectively altered on the gene expression and methylation *** an interpretable machine learning approach,DAM simultaneously considers the non-linear associations among samples and those among biological features,which should help explore interpretative biomarker candidates and efficient diagnostic models from multi-omics data analysis for human complexdiseases.

关键词： Deepsub space reconstruction Deepnon-negative matrix factorization Deepcanonical correlationanalysis Multi-omics Interpretable machine learning Childhood asthma

来源：评论

学校读者我要写书评

暂无评论

TIGER: A Generating-Then-Ranking Framework for Practical Python Type Inference

arXiv

引用

arXiv 2024年

作者： Wang, Chong Zhang, Jian Lou, Yiling Liu, Mingwei Sun, Weisong Liu, Yang Peng, Xin College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China School of Software Engineering Sun Yat-sen University China

Python’s dynamic typing system offers flexibility and expressiveness but can lead to type-related errors, prompting the need for automated type inference to enhance type hinting. While existing learning-based approaches show promising inference accuracy, they struggle with practical challenges in comprehensively handling various types, including complex parameterized types and (unseen) user-defined types. In this paper, we introduce TIGER, a two-stage generating-then-ranking (GTR) framework, designed to effectively handle Python’s diverse type categories. TIGER leverages fine-tuned pre-trained code models to train a generative model with a span masking objective and a similarity model with a contrastive training objective. This approach allows TIGER to generate a wide range of type candidates, including complex parameterized types in the generating stage, and accurately rank them with user-defined types in the ranking stage. Our evaluation on the ManyTypes4Py dataset shows TIGER’s advantage over existing methods in various type categories, notably improving accuracy in inferring user-defined and unseen types by 11.2% and 20.1% respectively in Top-5 Exact Match. Moreover, the experimental results not only demonstrate TIGER’s superior performance and efficiency, but also underscore the significance of its generating and ranking stages in enhancing automated type inference. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Multi-Stage Architecture for Pose Estimation of Zebrafish Head with Convolutional Neural Networks

引用

Journal of computer science & Technology 2021年第2期36卷 434-444页

作者： Zhang-Jin Huang Xiang-Xiang He Fang-Jun Wang Qing Shen School of Computer Science and Technology University of Science and Technology of ChinaHefei 230027China School of Data Science University of Science and Technology of ChinaHefei 230027China Anhui Province Key Laboratory of Software in Computing and Communication Hefei 230027China

In order to conduct optical neurophysiology experiments on a freely swimming zebrafish,it is essential to quantify the zebrafish head to determine exact lighting *** efficiently quantify a zebrafish head's behaviors with limited resources,we propose a real-time multi-stage architecture based on convolutional neural networks for pose estimation of the zebrafish head on *** stage is implemented with a small neural ***,a light-weight object detector named Micro-YOLO is used to detect a coarse region of the zebrafish head in the first *** the second stage,a tiny bounding box refinement network is devised to produce a high-quality bounding box around the zebrafish ***,a small pose estimation network named tiny-hourglass is designed to detect keypoints in the zebrafish *** experimental results show that using Micro-YOLO combined with RegressNet to predict the zebrafish head region is not only more accurate but also much faster than Faster R-CNN which is the representative of two-stage *** with DeepLabCut,a state-of-the-art method to estimate poses for user-defined body parts,our multi-stage architecture can achieve a higher accuracy,and runs 19x faster than it on CPUs.

关键词： convolutional neural network pose estimation real-time zebrafish

来源：评论

学校读者我要写书评

暂无评论

Time-Sensitive Local Differential Privacy-Based Federated Learning for Vehicular Digital Twin Networks 1st

Time-Sensitive Local Differential Privacy-Based Federated Le...

引用

1st International Symposium on Intelligent Computing and Networking, ISICN 2024

作者： Sun, Kangkang Xu, Hansong Zhang, Xiaojin Hua, Kun Li, Jianhua Shanghai Key Laboratory of Integrated Administration Technologies for Information Security School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Electrical Engineering California Polytechnic State University San Luis ObispoCA93407 United States

ISBN: (纸本)9783031674464

The Vehicular Digital Twin Network (VDTN) integrates digital twin (DT) models of connected and autonomous vehicles (CAVs) to facilitate smart sensing, management, and collaboration in the physical realm. VDTN synchronizes extensive data on roads, vehicles, and operators, including sensitive information like user location and driving habits. To address these privacy concerns and enhance model efficiency, we introduce a time-sensitive local differential privacy-based federated learning framework (FedTS) tailored for VDTN. This framework assigns varying privacy levels to DT models during model-sharing intervals, considering the time sensitivity of VDTNs. Comparative analysis with state-of-the-art algorithms, such as differentially-private stochastic gradient descent (DP-SGD), demonstrates significant improvements in both security and model performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Grading with Weakly-Supervised Lesion Priors 48

Diabetic Retinopathy Grading with Weakly-Supervised Lesion P...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Hou, Junlin Xiao, Fan Xu, Jilan Feng, Rui Zhang, Yuejie Zou, Haidong Lu, Lina Xue, Wenwen Fudan University School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai China Fudan University Academy for Engineering and Technology Shanghai China Shanghai Eye Diseases Prevention & Treatment Center Shanghai China

ISBN: (纸本)9781728163277

Explicit information of lesions can provide visual instructions for diabetic retinopathy (DR) grading on fundus images. However, pixel-level lesion annotations are extremely difficult and time-consuming to acquire. In this work, we propose a novel weakly-supervised lesion-aware network for DR grading, which enhances the discriminative features with lesion priors by only image-level supervision. Specifically, we design a lesion attention module that generates lesion activation maps by introducing an auxiliary task of binary DR identification. Lesion activation maps are utilized to assist the network to focus on the most relevant regions for boosting DR grading performance. Besides, we particularly devise an adaptive joint loss to balance the DR identification and DR grading tasks dynamically. Extensive results on the public DR dataset demonstrate the superiority and generality of our proposed lesion-aware network. The interpretability of generated lesion activation maps is also verified by the comparison with ground truth segmentation masks. © 2023 IEEE.

关键词： Activation map Diabetic retinopathy grading Fundus image Lesion priors Weakly-supervised

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：