检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Rütte, Dimitri Von Fluri, Janis Ding, Yuhui Orvieto, Antonio Schölkopf, Bernhard Hofmann, Thomas Data Analytics Lab Department of Computer Science ETH Zurich Switzerland ELLIS Institute Tübingen Tübingen AI Center Germany Max Planck Institute for Intelligent Systems Tübingen Germany

While state-of-the-art language models achieve impressive results through next-token prediction, they have inherent limitations such as the inability to revise already generated tokens. This has prompted exploration of alternative approaches such as discrete diffusion. However, masked diffusion, which has emerged as a popular choice due to its simplicity and effectiveness, reintroduces this inability to revise words. To overcome this, we generalize masked diffusion and derive the theoretical backbone of a family of general interpolating discrete diffusion (GIDD) processes offering greater flexibility in the design of the noising processes. Leveraging a novel diffusion ELBO, we achieve compute-matched state-of-the-art performance in diffusion language modeling. Exploiting GIDD’s flexibility, we explore a hybrid approach combining masking and uniform noise, leading to improved sample quality and unlocking the ability for the model to correct its own mistakes, an area where autoregressive models notoriously have struggled. Our code and models are open-source: https://***/dvruette/gidd/ © 2025, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

A General Framework for Clustering and Distribution Matching with Bandit Feedback

arXiv

引用

arXiv 2024年

作者： Yavas, Recep Can Huang, Yuqi Tan, Vincent Y.F. Scarlett, Jonathan Descartes Program CNRS@CREATE 138602 Singapore Department of Information Systems and Analytics School of Computing National University of Singapore 119077 Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Department of Computer Science Department of Mathematics Institute of Data Science National University of Singapore 119077 Singapore

We develop a general framework for clustering and distribution matching problems with bandit feedback. We consider a K-armed bandit model where some subset of K arms is partitioned into M groups. Within each group, the random variable associated to each arm follows the same distribution on a finite alphabet. At each time step, the decision maker pulls an arm and observes its outcome from the random variable associated to that arm. Subsequent arm pulls depend on the history of arm pulls and their outcomes. The decision maker has no knowledge of the distributions of the arms or the underlying partitions. The task is to devise an online algorithm to learn the underlying partition of arms with the least number of arm pulls on average and with an error probability not exceeding a pre-determined value δ. Several existing problems fall under our general framework, including finding M pairs of arms, odd arm identification, and N-ary clustering of K arms belong to our general framework. We derive a non-asymptotic lower bound on the average number of arm pulls for any online algorithm with an error probability not exceeding δ. Furthermore, we develop a computationally-efficient online algorithm based on the Track-and-Stop method and Frank–Wolfe algorithm, and show that the average number of arm pulls of our algorithm asymptotically matches that of the lower bound. Our refined analysis also uncovers a novel bound on the speed at which the average number of arm pulls of our algorithm converges to the fundamental limit as δ *** Codes 68T05 Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Shape-Driven Combined Approach for Breast Cancer Tumor Segmentation

Deep Learning and Shape-Driven Combined Approach for Breast ...

引用

International Conference on Advancements in Computational sciences (ICACS)

作者： Mudassar Ali Haoji Hu Tufail Muhammad Muhammad Ahsan Qureshi Tariq Mahmood College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Department of Computer Science Air University Islamabad Pakistan Artificial Intelligence and Data Analytics Lab CCIS Prince Sultan University Riyadh Kingdom of Saudi Arabia.

ISBN: (数字)9798331533038

ISBN: (纸本)9798331533045

Our aim is to enhance the performance of segmenting breast cancer from medical images by overcoming major challenges, including data insufficiency and complexity when training a model. Using the INbreast dataset, it proposes a hybrid method for improving the segmentation accuracy and computational efficiency by combining M3D-Neural Cellular Automata with Shape-Guided Segmentation. This work aims at optimal performance on complex tasks of tumor segmentation by leveraging shape priors and reducing the need for extensive training data. Results confirm that significant improvements in both accuracy and robustness are achieved, which reduces computation time and improves tumor boundary delineation. The hybrid approach provides a time- and cost-effective method for precise detection in breast cancer diagnosis and treatment.

关键词： Deep learning Training Image segmentation Accuracy Shape Training data Breast cancer data models Robustness Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Evaluating and Explaining Natural Language Generation with GenX 2

Evaluating and Explaining Natural Language Generation with G...

引用

2nd Workshop on data science with Human-in-the-Loop: Language Advances, DaSH-LA 2021

作者： Duskin, Kayla Sharma, Shivam Yun, Ji Young Saldanha, Emily Arendt, Dustin Data Science and Analytics Group Pacific Northwest National Laboratory United States Department of Computer Science New Jersey Institute of Technology United States Visual Analytics Group Pacific Northwest National Laboratory United States

ISBN: (纸本)9781954085398

Current methods for evaluation of natural language generation models focus on measuring text quality but fail to probe the model creativity, i.e., its ability to generate novel but coherent text sequences not seen in the training corpus. We present the GenX tool which is designed to enable interactive exploration and explanation of natural language generation outputs with a focus on the detection of memorization. We demonstrate the tool on two domain-conditioned generation use cases — phishing emails and ACL abstracts. © 2021 Association for Computational Linguistics

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

ClusterLDA: Clustering-Based Topic Extraction for Online News

ClusterLDA: Clustering-Based Topic Extraction for Online New...

引用

Women in data science at Prince Sultan University (WiDS PSU), International Conference of

作者： Juan Kenichi Sutan Jumanah Alshehri Rafaa Aljurbua Zoran Obradovic Department of Computer and Information Sciences Center for Data Analytics and Biomedical Informatics Temple University Philadelphia PA USA Department of Management Information Systems College of Business Administration Imam Abdulrahman bin Faisal University Dammam Saudi Arabia Department of Computer Science College of Computer Qassim University Buraydah Saudi Arabia

ISBN: (数字)9798331520922

ISBN: (纸本)9798331520939

Topic extraction from large text datasets is a critical task for understanding and analyzing thematic patterns across documents. This study explores three methods for improving topic modeling: standard Latent Dirichlet Allocation (LDA), a clustering-based approach combined with LDA, and an experimental method enhanced with Wikipedia-supplemented clustering. We demonstrate that applying clustering prior to LDA significantly improves topic extraction by aligning the modeling process with the natural structure of the data, allowing for the identification of smaller, yet meaningful, topics that are often overshadowed in standard LDA due to thematic imbalances. Additionally, we applied the improved topic modeling approach to construct an entity-topic network that contextualizes entities' sentiments within the topics they were mentioned in, providing a nuanced view of the dataset. Although our hypothesis that Wikipedia-enhanced clustering would further improve topic extraction was not supported, as it introduced noise and worsened performance, ClusterLDA approach proved effective in enhancing the granularity of topic extraction and addressing the limitations of standard LDA. These findings highlight the potential of clustering to support more coherent and semantically relevant topic extraction, offering a foundation for future advancements in topic modeling and sentiment analysis.

关键词： Text mining Electronic publishing Sentiment analysis Noise Encyclopedias data models Internet Online services Resource management Standards

来源：评论

学校读者我要写书评

暂无评论

Quantifying data Difficulty with Polarized K-Entropy for Assessing Machine Learning Models

Quantifying Data Difficulty with Polarized K-Entropy for Ass...

引用

IEEE International Conference on Information Reuse and Integration (IRI)

作者： Ayomide Afolabi Ramazan Aygun Truong X. Tran School of Data Science and Analytics Kennesaw State University Kennesaw GA USA Computer Science Department Kennesaw State University Kennesaw GA USA Penn State Harrisburg The Pennsylvania State University Middletown PA USA

ISBN: (数字)9798350351187

ISBN: (纸本)9798350351194

data difficulty level measurement is a critical aspect of machine learning performance evaluation. Several measures have been used to assess the difficulty level of classifying data points in binary classification. However, these measures typically involve building a machine learning model first, which is then used to assess the data difficulty level. In this paper, we propose a novel model agnostic measure named as polarized K-entropy to evaluate the difficulty of classifying a data instance. Our measure leverages the computation of entropy based on the nearest neighbors of a data point. We conducted experiments to evaluate the effectiveness of our proposed method by analyzing how the accuracy of machine learning models change with respect to data difficulty. We used Spearman’s rank correlation coefficient to analyze this relationship for neural network, support vector machine, and random forest. Our results show that our measure outperformed the non-conformity measure in all the experiments conducted for six datasets using the selected machine learning models.

关键词： Correlation coefficient Support vector machines Performance evaluation Accuracy Computational modeling Machine learning data models Entropy Rough surfaces Random forests

来源：评论

学校读者我要写书评

暂无评论

Addressing the Challenge of Missing Medical data in Healthcare analytics: A Focus on Machine Learning Predictions for ICU Length of Stay

Addressing the Challenge of Missing Medical Data in Healthca...

引用

Intermountain Engineering, Technology and Computing (IETC)

作者： Mahmad Isaq Karankot Max Marceau Ethan M. Glenn Rylan P. Fowers David M. Hedges Bonnie Sheehey Bradley M. Whitaker Electrical and Computer Engineering Montana State University Bozeman Montana USA Analytics/Data Science Department SelectHealth Murray Utah USA History and Philosophy Montana State University Bozeman Montana USA

ISBN: (数字)9798350373073

ISBN: (纸本)9798350373080

This research investigates the impact of missing data on the performance of machine learning algorithms, with a particular focus on the MIMIC-IV dataset. This project aims to investigate the extent to which missing data negatively impacts the training of machine learning algorithms, and whether demographic groups with a higher proportion of missing data (i.e.,ethnicity) have lower predictive accuracy. Using advanced machine learning and data analysis techniques, our results highlight important considerations related to missing data in medical datasets and provide useful insights for improving predictive modeling and decision support systems in clinical practice offers.

关键词： Training Decision support systems Machine learning algorithms MIMICs Machine learning Medical services Predictive models

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Clustering Split for Low-Bias Evaluation of Drug-Target Interaction Prediction

Hierarchical Clustering Split for Low-Bias Evaluation of Dru...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Bai, Peizhen Miljkovic, Filip Ge, Yan Greene, Nigel John, Bino Lu, Haiping University of Sheffield Department of Computer Science Sheffield United Kingdom Imaging and Data Analytics Clinical Pharmacology Safety Sciences RD AstraZeneca Gothenburg Sweden Imaging and Data Analytics Clinical Pharmacology Safety Sciences RD AstraZeneca Waltham United States

ISBN: (纸本)9781665401265

Drug-target interaction (DTI) prediction is important in drug discovery and chemogenomics studies. Machine learning, particularly deep learning, has advanced this area significantly over the past few years. However, a significant gap between the performance reported in academic papers and that in practical drug discovery settings, e.g. the random-split-based evaluation strategy tends to be too optimistic in estimating the prediction performance in real-world settings. Such performance gap is largely due to hidden data bias in experimental datasets and inappropriate data split. In this paper, we construct a low-bias DTI dataset and study more challenging data split strategies to improve performance evaluation for real-world settings. Specifically, we study the data bias in a popular DTI dataset, BindingDB, and re-evaluate the prediction performance of three state-of-the-art deep learning models using five different data split strategies: random split, cold drug split, scaffold split, and two hierarchical-clustering-based splits. In addition, we comprehensively examine six performance metrics. Our experimental results confirm the overoptimism of the popular random split and show that hierarchical-clustering-based splits are far more challenging and can provide potentially more useful assessment of model generalizability in real-world DTI prediction settings. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Transfer Neural Architecture Search Across Spaces via Representation Learning

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Hou, Boyu Feng, Liang Chen, Xuefeng Tang, Jing Tan, Kay Chen Liao, Xiaofeng Chongqing University College of Computer Science China Chongqing Key Laboratory of Big Data Intelligence and Privacy Computing Chongqing400044 China The Hong Kong Polytechnic University Department of Data Science and Artificial Intelligence Hong Kong999077 Hong Kong Data Science and Analytics Thrust Guangzhou511453 China

Neural Architecture Search (NAS) has emerged as a crucial method for automating the design of deep learning models. Despite its potential, NAS frequently requires substantial computational and hardware resources. To mitigate these challenges, transferable NAS (TNAS) has been introduced, leveraging prior NAS results to enhance performance on new tasks. However, existing methods largely focus on knowledge transfer within identical neural search spaces, overlooking the potential for cross-domain transferability. Motivated by this gap, we explore evolutionary TNAS across heterogeneous search spaces by learning common neural representations. In particular, we introduce a novel approach that encodes both operational and topological information of neural architectures into a unified sequence using a simple tokenizer. This sequence is then processed by a variational auto-encoder, with a Transformer-based encoder to capture rich neural representations and a decoder that reconstructs the original sequence. By utilizing these latent representations, we further establish an inter-domain mapping that acts as a bridge, enabling effective explicit solution transfer among diverse search spaces to enhance the evolutionary NAS process. To harness this capability, we develop an evolutionary sequential transfer optimization approach that transfers knowledge during population initialization, providing both flexibility and adaptability. To the best of our knowledge, this work serves as the first attempt in the literature exploring evolutionary TNAS across diverse spaces. Moreover, we demonstrate the utility of our method through comprehensive empirical studies using different architecture spaces, including NAS-Bench-101, NAS-Bench-201, and the DARTS search space. Our results show that the proposed method significantly enhances the adaptability and performance of NAS across varied domains. © 1997-2012 IEEE.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Strategies for Accurate Segmentation and Categorization of Unveiling Genetic Disorders in Bioinformatics

Artificial Intelligence Strategies for Accurate Segmentation...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： T. Sarathamani K. Kavitha C. Thirumoorthi K Jayanthi Vagini P. Manikandaprabhu P. Sumathi Department of Computer Science and Engineering (AI) Brainware University Kolkata India Department of AI and ML School of Computing Mohan Babu University Sree Sainath Nagar Tirupati India Department of Computer Science PSG College of Arts and Science Coimbatore Tamilnadu India Department of Computer science with Data Analytics KPR College of Arts Science and Research Coimbatore Tamilnadu India Department of Computer Science School of Computing Amrita Vishwa Vidyapeetham Mysuru Karnataka India Department of Computer Science Dr. G R Damodaran College of Science Coimbatore Tamilnadu India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Women all across the world are affected by the potentially fatal condition known as breast cancer. According to clinical experts, early cancer detection helps to save lives. Several machine learning algorithms have been developed to classify cancers in order to diagnose breast cancer, and medical image processing has been found to be a beneficial area for increasing classification accuracy. One of the most crucial signs for detecting breast cancer early is micro classifications. Machine learning methods have been employed in numerous studies to address this problem. Various classification algorithms are used to find the presence of breast cancer whether it is Benign or Malignant. For earlier cancer detection and diagnosis, an image enhancement approach is being developed. A machine learning technique is employed in this work to attempt to categorize breast cancer. The purpose of the present research was to increase the accuracy of machine learning methods for disease diagnosis using ML techniques.

关键词： Industries Image segmentation Accuracy Machine learning algorithms Machine learning Transforms Cancer detection Breast cancer Medical diagnosis Monitoring

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：