Proceedings of machine learning research最新文献_第8页

Fair admission risk prediction with proportional multicalibration. 比例多重校准的公平入场风险预测。

Proceedings of machine learning research Pub Date : 2023-01-01

William G La Cava, Elle Lett, Guangya Wan

{"title":"Fair admission risk prediction with proportional multicalibration.","authors":"William G La Cava, Elle Lett, Guangya Wan","doi":"","DOIUrl":"","url":null,"abstract":"Fair calibration is a widely desirable fairness criteria in risk prediction contexts. One way to measure and achieve fair calibration is with multicalibration. Multicalibration constrains calibration error among flexibly-defined subpopulations while maintaining overall calibration. However, multicalibrated models can exhibit a higher percent calibration error among groups with lower base rates than groups with higher base rates. As a result, it is possible for a decision-maker to learn to trust or distrust model predictions for specific groups. To alleviate this, we propose proportional multicalibration, a criteria that constrains the percent calibration error among groups and within prediction bins. We prove that satisfying proportional multicalibration bounds a model's multicalibration as well its differential calibration, a fairness criteria that directly measures how closely a model approximates sufficiency. Therefore, proportionally calibrated models limit the ability of decision makers to distinguish between model performance on different patient groups, which may make the models more trustworthy in practice. We provide an efficient algorithm for post-processing risk prediction models for proportional multicalibration and evaluate it empirically. We conduct simulation studies and investigate a real-world application of PMC-postprocessing to prediction of emergency department patient admissions. We observe that proportional multicalibration is a promising criteria for controlling simultaneous measures of calibration fairness of a model over intersectional groups with virtually no cost in terms of classification performance.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"209 ","pages":"350-378"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10417639/pdf/nihms-1917236.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10008223","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

Directed Graphical Models and Causal Discovery for Zero-Inflated Data. 零膨胀数据的有向图模型和因果发现。

Proceedings of machine learning research Pub Date : 2023-01-01

Shiqing Yu, Mathias Drton, Ali Shojaie

引用次数: 0

Skill, or Style? Classification of Fetal Sonography Eye-Tracking Data. 技能，还是风格？胎儿超声眼动追踪数据的分类。

Proceedings of machine learning research Pub Date : 2023-01-01

Clare Teng, Lior Drukker, Aris T Papageorghiou, J Alison Noble

引用次数: 0

Contrastive Representation Learning for Gaze Estimation. 用于凝视估计的对比表征学习

Proceedings of machine learning research Pub Date : 2023-01-01

Swati Jindal, Roberto Manduchi

{"title":"Contrastive Representation Learning for Gaze Estimation.","authors":"Swati Jindal, Roberto Manduchi","doi":"","DOIUrl":"","url":null,"abstract":"Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The task of gaze estimation, on the other hand, demands not just invariance to various appearances but also equivariance to the geometric transformations. In this work, we propose a simple contrastive representation learning framework for gaze estimation, named Gaze Contrastive Learning (GazeCLR). GazeCLR exploits multi-view data to promote equivariance and relies on selected data augmentation techniques that do not alter gaze directions for invariance learning. Our experiments demonstrate the effectiveness of GazeCLR for several settings of the gaze estimation task. Particularly, our results show that GazeCLR improves the performance of cross-domain gaze estimation and yields as high as 17.2% relative improvement. Moreover, the GazeCLR framework is competitive with state-of-the-art representation learning methods for few-shot evaluation. The code and pre-trained models are available at https://github.com/jswati31/gazeclr.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"210 ","pages":"37-49"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10270367/pdf/nihms-1862058.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9715239","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

Privacy-preserving patient clustering for personalized federated learning. 针对个性化联合学习的隐私保护患者聚类。

Proceedings of machine learning research Pub Date : 2023-01-01

Ahmed Elhussein, Gamze Gürsoy

{"title":"Privacy-preserving patient clustering for personalized federated learning.","authors":"Ahmed Elhussein, Gamze Gürsoy","doi":"","DOIUrl":"","url":null,"abstract":"Federated Learning (FL) is a machine learning framework that enables multiple organizations to train a model without sharing their data with a central server. However, it experiences significant performance degradation if the data is non-identically independently distributed (non-IID). This is a problem in medical settings, where variations in the patient population contribute significantly to distribution differences across hospitals. Personalized FL addresses this issue by accounting for site-specific distribution differences. Clustered FL, a Personalized FL variant, was used to address this problem by clustering patients into groups across hospitals and training separate models on each group. However, privacy concerns remained as a challenge as the clustering process requires exchange of patient-level information. This was previously solved by forming clusters using aggregated data, which led to inaccurate groups and performance degradation. In this study, we propose Privacy-preserving Community-Based Federated machine Learning (PCBFL), a novel Clustered FL framework that can cluster patients using patient-level data while protecting privacy. PCBFL uses Secure Multiparty Computation, a cryptographic technique, to securely calculate patient-level similarity scores across hospitals. We then evaluate PCBFL by training a federated mortality prediction model using 20 sites from the eICU dataset. We compare the performance gain from PCBFL against traditional and existing Clustered FL frameworks. Our results show that PCBFL successfully forms clinically meaningful cohorts of low, medium, and high-risk patients. PCBFL outperforms traditional and existing Clustered FL frameworks with an average AUC improvement of 4.3% and AUPRC improvement of 7.8%.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"219 ","pages":"150-166"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11376435/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142141965","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

SRDA: Mobile Sensing based Fluid Overload Detection for End Stage Kidney Disease Patients using Sensor Relation Dual Autoencoder. SRDA：基于移动传感的末期肾病患者体液超负荷检测（使用传感器关系双自动编码器）。

Proceedings of machine learning research Pub Date : 2023-01-01

Mingyue Tang, Jiechao Gao, Guimin Dong, Carl Yang, Bradford Campbell, Brendan Bowman, Jamie Marie Zoellner, Emaad Abdel-Rahman, Mehdi Boukhechba

引用次数: 0

Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression. 为患者风险进展建模的时间监督对比学习。

Proceedings of machine learning research Pub Date : 2023-01-01

Shahriar Noroozizadeh, Jeremy C Weiss, George H Chen

{"title":"Temporal Supervised Contrastive Learning for Modeling Patient Risk Progression.","authors":"Shahriar Noroozizadeh, Jeremy C Weiss, George H Chen","doi":"","DOIUrl":"","url":null,"abstract":"We consider the problem of predicting how the likelihood of an outcome of interest for a patient changes over time as we observe more of the patient's data. To solve this problem, we propose a supervised contrastive learning framework that learns an embedding representation for each time step of a patient time series. Our framework learns the embedding space to have the following properties: (1) nearby points in the embedding space have similar predicted class probabilities, (2) adjacent time steps of the same time series map to nearby points in the embedding space, and (3) time steps with very different raw feature vectors map to far apart regions of the embedding space. To achieve property (3), we employ a nearest neighbor pairing mechanism in the raw feature space. This mechanism also serves as an alternative to \"data augmentation\", a key ingredient of contrastive learning, which lacks a standard procedure that is adequately realistic for clinical tabular data, to our knowledge. We demonstrate that our approach outperforms state-of-the-art baselines in predicting mortality of septic patients (MIMIC-III dataset) and tracking progression of cognitive impairment (ADNI dataset). Our method also consistently recovers the correct synthetic dataset embedding structure across experiments, a feat not achieved by baselines. Our ablation experiments show the pivotal role of our nearest neighbor pairing.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"225 ","pages":"403-427"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10976929/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140320101","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

Multiple Imputation with Neural Network Gaussian Process for High-dimensional Incomplete Data. 高维不完整数据的神经网络高斯过程多重插值。

Proceedings of machine learning research Pub Date : 2022-12-01

Zongyu Dai, Zhiqi Bu, Qi Long

{"title":"Multiple Imputation with Neural Network Gaussian Process for High-dimensional Incomplete Data.","authors":"Zongyu Dai, Zhiqi Bu, Qi Long","doi":"","DOIUrl":"","url":null,"abstract":"Missing data are ubiquitous in real world applications and, if not adequately handled, may lead to the loss of information and biased findings in downstream analysis. Particularly, high-dimensional incomplete data with a moderate sample size, such as analysis of multi-omics data, present daunting challenges. Imputation is arguably the most popular method for handling missing data, though existing imputation methods have a number of limitations. Single imputation methods such as matrix completion methods do not adequately account for imputation uncertainty and hence would yield improper statistical inference. In contrast, multiple imputation (MI) methods allow for proper inference but existing methods do not perform well in high-dimensional settings. Our work aims to address these significant methodological gaps, leveraging recent advances in neural network Gaussian process (NNGP) from a Bayesian viewpoint. We propose two NNGP-based MI methods, namely MI-NNGP, that can apply multiple imputations for missing values from a joint (posterior predictive) distribution. The MI-NNGP methods are shown to significantly outperform existing state-of-the-art methods on synthetic and real datasets, in terms of imputation error, statistical inference, robustness to missing rates, and computation costs, under three missing data mechanisms, MCAR, MAR, and MNAR. Code is available in the GitHub repository https://github.com/bestadcarry/MI-NNGP.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"189 ","pages":"265-279"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10348708/pdf/nihms-1861886.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9821494","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

Meta-analysis of individualized treatment rules via sign-coherency 基于符号一致性的个体化治疗规则元分析

Proceedings of machine learning research Pub Date : 2022-11-28 DOI: 10.48550/arXiv.2211.15476

Jay Jojo Cheng, J. Huling, Guanhua Chen

{"title":"Meta-analysis of individualized treatment rules via sign-coherency","authors":"Jay Jojo Cheng, J. Huling, Guanhua Chen","doi":"10.48550/arXiv.2211.15476","DOIUrl":"https://doi.org/10.48550/arXiv.2211.15476","url":null,"abstract":"Medical treatments tailored to a patient's baseline characteristics hold the potential of improving patient outcomes while reducing negative side effects. Learning individualized treatment rules (ITRs) often requires aggregation of multiple datasets(sites); however, current ITR methodology does not take between-site heterogeneity into account, which can hurt model generalizability when deploying back to each site. To address this problem, we develop a method for individual-level meta-analysis of ITRs, which jointly learns site-specific ITRs while borrowing information about feature sign-coherency via a scientifically-motivated directionality principle. We also develop an adaptive procedure for model tuning, using information criteria tailored to the ITR learning problem. We study the proposed methods through numerical experiments to understand their performance under different levels of between-site heterogeneity and apply the methodology to estimate ITRs in a large multi-center database of electronic health records. This work extends several popular methodologies for estimating ITRs (A-learning, weighted learning) to the multiple-sites setting.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"193 1","pages":"171-198"},"PeriodicalIF":0.0,"publicationDate":"2022-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47047493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multiple Imputation with Neural Network Gaussian Process for High-dimensional Incomplete Data 高维不完全数据的神经网络高斯过程多重脉冲

Proceedings of machine learning research Pub Date : 2022-11-23 DOI: 10.48550/arXiv.2211.13297

Zongyu Dai, Zhiqi Bu, Q. Long

{"title":"Multiple Imputation with Neural Network Gaussian Process for High-dimensional Incomplete Data","authors":"Zongyu Dai, Zhiqi Bu, Q. Long","doi":"10.48550/arXiv.2211.13297","DOIUrl":"https://doi.org/10.48550/arXiv.2211.13297","url":null,"abstract":"Missing data are ubiquitous in real world applications and, if not adequately handled, may lead to the loss of information and biased findings in downstream analysis. Particularly, high-dimensional incomplete data with a moderate sample size, such as analysis of multi-omics data, present daunting challenges. Imputation is arguably the most popular method for handling missing data, though existing imputation methods have a number of limitations. Single imputation methods such as matrix completion methods do not adequately account for imputation uncertainty and hence would yield improper statistical inference. In contrast, multiple imputation (MI) methods allow for proper inference but existing methods do not perform well in high-dimensional settings. Our work aims to address these significant methodological gaps, leveraging recent advances in neural network Gaussian process (NNGP) from a Bayesian viewpoint. We propose two NNGP-based MI methods, namely MI-NNGP, that can apply multiple imputations for missing values from a joint (posterior predictive) distribution. The MI-NNGP methods are shown to significantly outperform existing state-of-the-art methods on synthetic and real datasets, in terms of imputation error, statistical inference, robustness to missing rates, and computation costs, under three missing data mechanisms, MCAR, MAR, and MNAR. Code is available in the GitHub repository https://github.com/bestadcarry/MI-NNGP.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"189 1","pages":"265-279"},"PeriodicalIF":0.0,"publicationDate":"2022-11-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43147782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2