检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingzhe Dai Xiaoshuang Shi Xiaofeng Zhu Tingrui Pan Kang Li School of Software Engineering University of Science and Technology of China Hefei China West China Biomedical Big Data Center West China Hospital of Sichuan University Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Sichuan Artificial Intelligence Research Institute Yibin China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Deep multiple instance learning (MIL) has attracted considerable attention in medical image analysis, since it only requires image-level labels for model training without using fine-grained (or patch) annotations. Unfortunately, MIL-based methods might lose some significant patch features. Although pseudo-label-based methods, which assign a pre-defined label to each patch, can explore more patch-level features, they might bring label noise and make the patch-level features lose diversity, thereby possibly restricting the model performance. To overcome this issue, we propose a novel gradient-based patch target generation (PTG) module to dynamically produce a feature vector for each patch as its target. Additionally, based on the PTG module, we propose a patch-target guided dual-branch deep MIL framework for 3D MRI data analysis, where both the two branches consist of a CNN model to extract patch-level features, an attention module to interpret the significance of patches, and a bag-level classifier, while the second branch also contains the PTG module to generate patch targets of patches. Moreover, the two branches are alternatively updated in our framework, resulting in a bi-level optimization problem, and thus we design a bi-level optimization algorithm to solve our proposed objective function. Extensive experiments demonstrate the superior classification and interpretation performance of the proposed framework over recent state-of-the-art methods. Codes are available at https://***/daimz1213/mil2024.

关键词： Training Analytical models Solid modeling Three-dimensional displays Annotations Magnetic resonance imaging Feature extraction Vectors Optimization Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Investigating the Big data Challenges of Deep Learning for data science

Investigating the Big Data Challenges of Deep Learning for D...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), International Conference on

作者： Prateek Aggarwal Shweta Singh Krishnan Batri N.T. Velusudha Sunil D. Kale Gajendra Shrimal Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and technology Chitkara University Punjab India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India School of Computer Science and Engineering Jain (Deemed to be University) Bangalore Karnataka India Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Artificial Intelligence & Data Science Vishwakarma Institute of Information Technology Pune India Department of Computer Science & Engineering Vivekananda Global University Jaipur India

Deep-gaining knowledge is a subset of synthetic intelligence (AI) that employs superior technology, data mining, and system-gaining knowledge to use massive datasets to find insights and styles. It is an area of advanced computing technology that enables computer systems to get the right of entry to analyze and analyze from many statistics. Even as the ability of deep learning is enormous, where its impact remains uncovered, extensive statistics demanding situations lie at the crossroads of its software and effectiveness. Massive records datasets' high quality and shape are essential for successfully implementing deep studying fashions. There may be an increasing need for highly acceptable statistics, including correctly categorized information, for training deep learning fashions. Moreover, deep studying often requires big datasets to provide correct output. It, therefore, calls for records to be amassed from numerous assets, posing the need for more homogeneous, regular, and standardized information. Adequate statistics garage, processing, and analytic solutions must be followed to analyze massive facts to create reachable and usable datasets for successful deep mastering packages. It includes infrastructure capable of securely keeping a large amount of information, in addition to the cloud-based totally systems to efficiently method extensive quantities of statistics. There has been a shift in the direction of using “large records” technologies like Apache Hadoop, Apache Spark, and different associated libraries. Even as deep mastering holds massive capability for uncovering new insights and turning in gigantic value to fields which include healthcare, finance, enterprise control, and more incredible, the associated massive data demanding situations ought to be addressed for those programs to reach their full capability. Despite the present-day challenges, advances in extensive records solutions like Apache Hadoop and Apache Spark, coupled with advanced analytic

关键词：

来源：评论

学校读者我要写书评

暂无评论

SELF-TRANSRIBER: FEW-SHOT LYRICS TRANSCRIPTION WITH SELF-TRAINING

arXiv

引用

arXiv 2022年

作者： Gao, Xiaoxue Yue, Xianghu Li, Haizhou Department of Electrical and Computer Engineering National University of Singapore Singapore Shenzhen Research Institute of Big Data Shenzhen China School of Data Science The Chinese University of Hong Kong Shenzhen China

The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem have not been explored for lyrics transcription. We propose the first semi-supervised lyrics transcription paradigm, Self-Transcriber, by leveraging on unlabeled data using self-training with noisy student augmentation. We attempt to demonstrate the possibility of lyrics transcription with a few amount of labeled data. Self-Transcriber generates pseudo labels of the unlabeled singing using teacher model, and augments pseudo-labels to the labeled data for student model update with both self-training and supervised training losses. This work closes the gap between supervised and semi-supervised learning as well as opens doors for few-shot learning of lyrics transcription. Our experiments show that our approach using only 12.7 hours of labeled data achieves competitive performance compared with the supervised approaches trained on 149.1 hours of labeled data for lyrics transcription. © 2022, CC BY-NC-ND.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

GANs-guided Conditional Diffusion Model for Synthesizing Contrast-enhanced Computed Tomography Images

GANs-guided Conditional Diffusion Model for Synthesizing Con...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yulin Yang Jing Liu Qingqing Chen Yinhao Li Xian-Hua Han Hongjie Hu Lanfen Lin Yen-Wei Chen Gradate School of Information Science and Engineering Ritsumeikan University Shiga Japan Research Center for Healthcare Data Science Zhejiang Lab. Hangzhou China Department of Radiology of Sir Run Run Shaw Hospital Zhejiang University School of Medicine Hangzhou China College of Information Science and Engineering Ritsumeikan University Shiga Japan Artificial Intelligence Research Center Yamaguchi University Yamaguchi Japan College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

In contrast to non-contrast computed tomography (NC-CT) scans, contrast-enhanced (CE) CT scans can highlight discrepancies between abnormal and normal areas, commonly used in clinical diagnosis of focal liver lesions. However, the use of contrast agents in CE-CT scans imposes significant physical and economic burdens on patients in clinical practice. Recently, Generative Adversarial Networks (GANs)-based synthesis models offer an alternative approach that obtains CE-CT images from NC-CT images. However, poor coverage and mode collapse greatly limit their performance. Diffusion models (DMs)-based methods have demonstrated superior performance in natural image synthesis tasks. Nevertheless, our experiment shows that CE-CT images synthesized from DMs-based method exhibit higher overall quality but lower local quality. The quality of local areas, particularly those related to lesion areas, is crucial in medical image synthesis tasks. Hence, we propose a GANs-guided conditional diffusion model (GANs-CDM), combining the GANs and conditional diffusion model (CDM), to generate CECT images. In the proposed GANs-CDM, the GANs is to generate a preliminary CE-CT image, serving as conditional input for guiding the subsequent CDM to produce refined CE-CT images. Qualitative and quantitative evaluation on arterial and portal venous phase synthesis tasks demonstrates that our proposed GANs-CDM can significantly improve both the local and global quality of synthetic images.

关键词： Economics Image synthesis Computed tomography Biological system modeling Liver Diffusion models Generative adversarial networks Lesions Portals Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

SP3: Enhancing Structured Pruning via PCA Projection

arXiv

引用

arXiv 2023年

作者： Hu, Yuxuan Zhang, Jing Zhao, Zhe Zhao, Chen Chen, Xiaodong Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China Engineering Research Center of Database and Business Intelligence MOE China Tencent AI Lab Tencent Beijing China School of Computer Science and Technology Xi'an Jiaotong University Xi'An China

Structured pruning is a widely used technique for reducing the size of pre-trained language models (PLMs), but current methods often overlook the potential of compressing the hidden dimension (d) in PLMs, a dimension critical to model size and efficiency. This paper introduces a novel structured pruning approach, Structured Pruning with PCA Projection (SP3), targeting the effective reduction of d by projecting features into a space defined by principal components before masking. Extensive experiments on benchmarks (GLUE and SQuAD) show that SP3 can reduce d by 70%, compress 94% of the BERTbase model, and maintain over 96% accuracy and outperform other methods that compress d by 6% in accuracy at the same compression ratio. SP3 has also proven effective with other models, including OPT and Llama. Our data and code are available at ours repo. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation

arXiv

引用

arXiv 2024年

作者： Zhang, Xianzhi Zhou, Yipeng Hu, Miao Wu, Di Liao, Pengshan Guizani, Mohsen Sheng, Michael The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China The Department of Computing Faculty of Science and Engineering Macquarie University Sydney Australia The Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates

To mitigate the rising concern about privacy leakage, the federated recommender (FR) paradigm emerges, in which decentralized clients co-train the recommendation model without exposing their raw user-item rating data. The differentially private federated recommender (DPFR) further enhances FR by injecting differentially private (DP) noises into clients. Yet, current DPFRs, suffering from noise distortion, cannot achieve satisfactory accuracy. Various efforts have been dedicated to improving DPFRs by adaptively allocating the privacy budget over the learning process. However, due to the intricate relation between privacy budget allocation and model accuracy, existing works are still far from maximizing DPFR accuracy. To address this challenge, we develop BGTplanner (Budget Planner) to strategically allocate the privacy budget for each round of DPFR training, improving overall training performance. Specifically, we leverage the Gaussian process regression and historical information to predict the change in recommendation accuracy with a certain allocated privacy budget. Additionally, Contextual Multi-Armed Bandit (CMAB) is harnessed to make privacy budget allocation decisions by reconciling the current improvement and long-term privacy constraints. Our extensive experimental results on real datasets demonstrate that BGTplanner achieves an average improvement of 6.76% in training performance compared to state-of-the-art baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Generalized Category Discovery with Decoupled Prototypical Network

arXiv

引用

arXiv 2022年

作者： An, Wenbin Tian, Feng Zheng, Qinghua Ding, Wei Wang, QianYing Chen, Ping School of Automation Science and Engineering Xi’an Jiaotong University China School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Laboratory for Big Data Analytics China Department of Computer Science University of Massachusetts Boston United States Lenovo Research Department of Engineering University of Massachusetts Boston United States

Generalized Category Discovery (GCD) aims to recognize both known and novel categories from a set of unlabeled data, based on another dataset labeled with only known categories. Without considering differences between known and novel categories, current methods learn about them in a coupled manner, which can hurt model’s generalization and discriminative ability. Furthermore, the coupled training approach prevents these models transferring category-specific knowledge explicitly from labeled data to unlabeled data, which can lose high-level semantic information and impair model performance. To mitigate above limitations, we present a novel model called Decoupled Prototypical Network (DPN). By formulating a bipartite matching problem for category prototypes, DPN can not only decouple known and novel categories to achieve different training targets effectively, but also align known categories in labeled and unlabeled data to transfer category-specific knowledge explicitly and capture high-level semantics. Furthermore, DPN can learn more discriminative features for both known and novel categories through our proposed Semantic-aware Prototypical Learning (SPL). Besides capturing meaningful semantic information, SPL can also alleviate the noise of hard pseudo labels through semantic-weighted soft assignment. Extensive experiments show that DPN outperforms state-of-the-art models by a large margin on all evaluation metrics across multiple benchmark datasets. Code and data are available at https://***/Lackel/DPN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection

arXiv

引用

arXiv 2022年

作者： Wan, Wei Hu, Shengshan Lu, Jianrong Yu Zhang, Leo Jin, Hai He, Yuanyuan School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab School of Information Technology Deakin University Australia

Federated learning (FL) enables multiple clients to collaboratively train an accurate global model while protecting clients’ data privacy. However, FL is susceptible to Byzantine attacks from malicious participants. Although the problem has gained significant attention, existing defenses have several flaws: the server irrationally chooses malicious clients for aggregation even after they have been detected in previous rounds;the defenses perform ineffectively against sybil attacks or in the heterogeneous data setting. To overcome these issues, we propose MAB-RFL, a new method for robust aggregation in FL. By modelling the client selection as an extended multi-armed bandit (MAB) problem, we propose an adaptive client selection strategy to choose honest clients that are more likely to contribute high-quality updates. We then propose two approaches to identify malicious updates from sybil and non-sybil attacks, based on which rewards for each client selection decision can be accurately evaluated to discourage malicious behaviors. MAB-RFL achieves a satisfying balance between exploration and exploitation on the potential benign clients. Extensive experimental results show that MAB-RFL outperforms existing defenses in three attack scenarios under different percentages of attackers. Copyright © 2022, The Authors. All rights reserved.

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Method for Thyroid Nodule Detection and Evaluation in Ultrasound Images

Advanced Deep Learning Method for Thyroid Nodule Detection a...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Sesha Vidhya S Swagata Sarkar Rashmi B R Suseendra R Prakash Kumar P S Srimathi S Department of ECE RMK College of Engineering and Technology Department of Artificial intelligence and Data Science Sri Sairam Engineering College Sai Leo Nagar West Tambaram Chennai 44 Department of Computer Science and Engineering Raja Rajeswari College of Engineering Kumbalgodu Karnataka Department of Information Technology Panimalar Engineering College Department of Information Technology K S R Institute for Engineering and Technology Tiruchengode Namakkal Department of Bio Technology Saveetha School of Engineering SIMATS Chennai Tamilnadu India

Thyroid nodule detection in its earliest stages is a difficult endeavor. Thyroid nodule diagnosis requires a lot of time and effort if done manually. The original ultrasound imaging of thyroid nodules is very variable due to differences in equipment and technicians. The issue with nodules is determining whether or not they are cancerous. Thyroid nodule evaluation through ultrasonography is presently advised as the first line of treatment. Ultrasound imaging can be helpful in making a diagnosis; But this relies heavily on the proficiency of the radiologist. There is a great need for faster and more efficient automated techniques of screening ultrasound pictures. This research study presents a deep learning method to detect thyroid nodules quickly and accurately. Some image processing techniques are required for optimal utilization of ultrasound imaging data of thyroid nodules. In this study, authors used deep neural networks InceptionResnet V2 and image augmentation to create a system for autonomous thyroid nodule categorization. For testing, neural networks with four-layer network nodes and the Local Laplacian Filtering technique are used to improve the image quality. The proposed method's reliability is evaluated by using the Thyroid Digital Image database (TDID), a freely available dataset. The comparative findings demonstrate that the proposed method is superior to the current state of advancement in machine learning. Based on experiments, it is evident that the proposed technique has an Accuracy 0.99, Precision 0.98, Recall 0.96, Fl-Score 0.98, AVC-ROC 0.99.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RecCoder: Reformulating Sequential Recommendation as Large Language Model-Based Code Completion

RecCoder: Reformulating Sequential Recommendation as Large L...

引用

IEEE International Conference on data Mining (ICDM)

作者： Kai-Huang Lai Wu-Dong Xi Xing-Xing Xing Wei Wan Chang-Dong Wang Min Chen Mohsen Guizani School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Contribution during internship at NetEase Games UX Center NetEase Games Guangzhou China Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangzhou China School of Computer Science and Engineering South China University of Technology Guangzhou China Pazhou Laboratory Guangzhou China Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI) Abu Dhabi UAE

ISBN: (数字)9798331506681

ISBN: (纸本)9798331506698

In the evolving landscape of sequential recommendation systems, the application of Large Language Models (LLMs) is increasingly prominent. However, current attempts typically utilize general-purpose LLMs, which present a mismatch in capability and a large semantic gap relative to the specialized needs of recommendation tasks. To tackle these issues, we introduce RecCoder, an innovative model that reformulates sequential recommendation as a code completion task. This approach leverages the superior reasoning capability of code LLMs as a backbone, aligning well with the requirements of recommendation systems. To bridge the semantic gap, RecCoder creates extra tokens for each item and employs item content to initialize token embeddings. Furthermore, we have developed a suite of Semantic Adaptation Fine-tuning tasks, tailored to enhance the model's acquisition of both content and collaborative semantic information, thus aligning the model's intrinsic capabilities with the unique demands of recommendation tasks. Through extensive testing on three public datasets, RecCoder has shown remarkable improvements over existing models in terms of recommendation accuracy and efficiency. This success highlights the substantial yet previously underexplored potential of code LLMs in improving recommendation accuracy and efficiency, suggesting a promising new direction for future research in this area. The implementation code is accessible at https://***/AllminerLab/Code-for-RecCoder-master.

关键词： Adaptation models Codes Accuracy Large language models Semantics Cognition data models data mining Recommender systems Testing

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：