Patterns最新文献

Integration of large language models and federated learning.

IF 6.7

Patterns Pub Date : 2024-12-13 DOI: 10.1016/j.patter.2024.101098

Chaochao Chen, Xiaohua Feng, Yuyuan Li, Lingjuan Lyu, Jun Zhou, Xiaolin Zheng, Jianwei Yin

{"title":"Integration of large language models and federated learning.","authors":"Chaochao Chen, Xiaohua Feng, Yuyuan Li, Lingjuan Lyu, Jun Zhou, Xiaolin Zheng, Jianwei Yin","doi":"10.1016/j.patter.2024.101098","DOIUrl":"https://doi.org/10.1016/j.patter.2024.101098","url":null,"abstract":"As the parameter size of large language models (LLMs) continues to expand, there is an urgent need to address the scarcity of high-quality data. In response, existing research has attempted to make a breakthrough by incorporating federated learning (FL) into LLMs. Conversely, considering the outstanding performance of LLMs in task generalization, researchers have also tried applying LLMs within FL to tackle challenges in relevant domains. The complementarity between LLMs and FL has already ignited widespread research interest. In this review, we aim to deeply explore the integration of LLMs and FL. We propose a research framework dividing the fusion of LLMs and FL into three parts: the combination of LLM sub-technologies with FL, the integration of FL sub-technologies with LLMs, and the overall merger of LLMs and FL. We first provide a comprehensive review of the current state of research in the domain of LLMs combined with FL, including their typical applications, integration advantages, challenges faced, and future directions for resolution. Subsequently, we discuss the practical applications of the combination of LLMs and FL in critical scenarios such as healthcare, finance, and education and provide new perspectives and insights into future research directions for LLMs and FL.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"5 12","pages":"101098"},"PeriodicalIF":6.7,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11701858/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142956218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data-knowledge co-driven innovations in engineering and management.

IF 6.7

Patterns Pub Date : 2024-12-13 DOI: 10.1016/j.patter.2024.101114

Yingji Xia, Xiqun Michael Chen, Sudan Sun

引用次数: 0

Decorrelative network architecture for robust electrocardiogram classification.

IF 6.7

Patterns Pub Date : 2024-12-09 eCollection Date: 2024-12-13 DOI: 10.1016/j.patter.2024.101116

Christopher Wiedeman, Ge Wang

{"title":"Decorrelative network architecture for robust electrocardiogram classification.","authors":"Christopher Wiedeman, Ge Wang","doi":"10.1016/j.patter.2024.101116","DOIUrl":"https://doi.org/10.1016/j.patter.2024.101116","url":null,"abstract":"To achieve adequate trust in patient-critical medical tasks, artificial intelligence must be able to recognize instances where they cannot operate confidently. Ensemble methods are deployed to estimate uncertainty, but models in an ensemble often share the same vulnerabilities to adversarial attacks. We propose an ensemble approach based on feature decorrelation and Fourier partitioning for teaching networks diverse features, reducing the chance of perturbation-based fooling. We test our approach against white-box attacks in single- and multi-channel electrocardiogram classification and adapt adversarial training and DVERGE into an ensemble framework for comparison. Our results indicate that the combination of decorrelation and Fourier partitioning maintains performance on unperturbed data while demonstrating superior uncertainty estimation on projected gradient descent and smooth adversarial attacks of various magnitudes. Furthermore, our approach does not require expensive optimization with adversarial samples during training. These methods can be applied to other tasks for more robust models.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"5 12","pages":"101116"},"PeriodicalIF":6.7,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11701855/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142956216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Best holdout assessment is sufficient for cancer transcriptomic model selection.

IF 6.7

Patterns Pub Date : 2024-12-06 eCollection Date: 2024-12-13 DOI: 10.1016/j.patter.2024.101115

Jake Crawford, Maria Chikina, Casey S Greene

{"title":"Best holdout assessment is sufficient for cancer transcriptomic model selection.","authors":"Jake Crawford, Maria Chikina, Casey S Greene","doi":"10.1016/j.patter.2024.101115","DOIUrl":"https://doi.org/10.1016/j.patter.2024.101115","url":null,"abstract":"Guidelines in statistical modeling for genomics hold that simpler models have advantages over more complex ones. Potential advantages include cost, interpretability, and improved generalization across datasets or biological contexts. We directly tested the assumption that small gene signatures generalize better by examining the generalization of mutation status prediction models across datasets (from cell lines to human tumors and vice versa) and biological contexts (holding out entire cancer types from pan-cancer data). We compared model selection between solely cross-validation performance and combining cross-validation performance with regularization strength. We did not observe that more regularized signatures generalized better. This result held across both generalization problems and for both linear models (LASSO logistic regression) and non-linear ones (neural networks). When the goal of an analysis is to produce generalizable predictive models, we recommend choosing the ones that perform best on held-out data or in cross-validation instead of those that are smaller or more regularized.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"5 12","pages":"101115"},"PeriodicalIF":6.7,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11701843/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142956206","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The recent Physics and Chemistry Nobel Prizes, AI, and the convergence of knowledge fields.

IF 6.7

Patterns Pub Date : 2024-11-25 eCollection Date: 2024-12-13 DOI: 10.1016/j.patter.2024.101099

Charles H Martin, Ganesh Mani

引用次数: 0

Cross-modal contrastive learning for unified placenta analysis using photographs.

IF 6.7

Patterns Pub Date : 2024-11-19 eCollection Date: 2024-12-13 DOI: 10.1016/j.patter.2024.101097

Yimu Pan, Manas Mehta, Jeffery A Goldstein, Joseph Ngonzi, Lisa M Bebell, Drucilla J Roberts, Chrystalle Katte Carreon, Kelly Gallagher, Rachel E Walker, Alison D Gernand, James Z Wang

{"title":"Cross-modal contrastive learning for unified placenta analysis using photographs.","authors":"Yimu Pan, Manas Mehta, Jeffery A Goldstein, Joseph Ngonzi, Lisa M Bebell, Drucilla J Roberts, Chrystalle Katte Carreon, Kelly Gallagher, Rachel E Walker, Alison D Gernand, James Z Wang","doi":"10.1016/j.patter.2024.101097","DOIUrl":"https://doi.org/10.1016/j.patter.2024.101097","url":null,"abstract":"The placenta is vital to maternal and child health but often overlooked in pregnancy studies. Addressing the need for a more accessible and cost-effective method of placental assessment, our study introduces a computational tool designed for the analysis of placental photographs. Leveraging images and pathology reports collected from sites in the United States and Uganda over a 12-year period, we developed a cross-modal contrastive learning algorithm consisting of pre-alignment, distillation, and retrieval modules. Moreover, the proposed robustness evaluation protocol enables statistical assessment of performance improvements, provides deeper insight into the impact of different features on predictions, and offers practical guidance for its application in a variety of settings. Through extensive experimentation, our tool demonstrates an average area under the receiver operating characteristic curve score of over 82% in both internal and external validations, which underscores the potential of our tool to enhance clinical care across diverse environments.","PeriodicalId":36242,"journal":{"name":"Patterns","volume":"5 12","pages":"101097"},"PeriodicalIF":6.7,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11701861/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142956210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exploring the hidden world of RNA viruses with a transformer-based tool. 利用基于变压器的工具探索 RNA 病毒的隐秘世界。

IF 6.7

Patterns Pub Date : 2024-11-08 DOI: 10.1016/j.patter.2024.101095

So Nakagawa, Shoichi Sakaguchi

引用次数: 0

Hopfield and Hinton's neural network revolution and the future of AI. Hopfield 和 Hinton 的神经网络革命与人工智能的未来。

IF 6.7

Patterns Pub Date : 2024-11-08 DOI: 10.1016/j.patter.2024.101094

James Z Wang, Brad Wyble

引用次数: 0

Privacy of single-cell gene expression data. 单细胞基因表达数据的隐私。