Proceedings of machine learning research最新文献_第9页

DIET: Conditional independence testing with marginal dependence measures of residual information DIET：剩余信息的边际依赖性度量的条件独立性检验

Proceedings of machine learning research Pub Date : 2022-08-18 DOI: 10.48550/arXiv.2208.08579

Mukund Sudarshan, A. Puli, Wesley Tansey, R. Ranganath

{"title":"DIET: Conditional independence testing with marginal dependence measures of residual information","authors":"Mukund Sudarshan, A. Puli, Wesley Tansey, R. Ranganath","doi":"10.48550/arXiv.2208.08579","DOIUrl":"https://doi.org/10.48550/arXiv.2208.08579","url":null,"abstract":"Conditional randomization tests (CRTs) assess whether a variable x is predictive of another variable y, having observed covariates z. CRTs require fitting a large number of predictive models, which is often computationally intractable. Existing solutions to reduce the cost of CRTs typically split the dataset into a train and test portion, or rely on heuristics for interactions, both of which lead to a loss in power. We propose the decoupled independence test (DIET), an algorithm that avoids both of these issues by leveraging marginal independence statistics to test conditional independence relationships. DIET tests the marginal independence of two random variables: Fx∣z(x∣z) and Fy∣z(y∣z) where F⋅∣z(⋅∣z) is a conditional cumulative distribution function (CDF) for the distribution p(⋅∣z). These variables are termed \"information residuals.\" We give sufficient conditions for DIET to achieve finite sample type-1 error control and power greater than the type-1 error rate. We then prove that when using the mutual information between the information residuals as a test statistic, DIET yields the most powerful conditionally valid test. Finally, we show DIET achieves higher power than other tractable CRTs on several synthetic and real benchmarks.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"206 1","pages":"10343-10367"},"PeriodicalIF":0.0,"publicationDate":"2022-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43051329","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: 1

Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness 临床存在下的推断策略：对算法公平性的影响

Proceedings of machine learning research Pub Date : 2022-08-13 DOI: 10.48550/arXiv.2208.06648

V. Jeanselme, Maria De-Arteaga, Zhe Zhang, J. Barrett, Brian D. M. Tom

{"title":"Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness","authors":"V. Jeanselme, Maria De-Arteaga, Zhe Zhang, J. Barrett, Brian D. M. Tom","doi":"10.48550/arXiv.2208.06648","DOIUrl":"https://doi.org/10.48550/arXiv.2208.06648","url":null,"abstract":"Biases have marked medical history, leading to unequal care affecting marginalised groups. The patterns of missingness in observational data often reflect these group discrepancies, but the algorithmic fairness implications of group-specific missingness are not well understood. Despite its potential impact, imputation is too often an overlooked preprocessing step. When explicitly considered, attention is placed on overall performance, ignoring how this preprocessing can reinforce groupspecific inequities. Our work questions this choice by studying how imputation affects downstream algorithmic fairness. First, we provide a structured view of the relationship between clinical presence mechanisms and groupspecific missingness patterns. Then, through simulations and real-world experiments, we demonstrate that the imputation choice influences marginalised group performance and that no imputation strategy consistently reduces disparities. Importantly, our results show that current practices may endanger health equity as similarly performing imputation strategies at the population level can affect marginalised groups differently. Finally, we propose recommendations for mitigating inequities that may stem from a neglected step of the machine learning pipeline.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"193 1","pages":"12 - 34"},"PeriodicalIF":0.0,"publicationDate":"2022-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43981392","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: 3

Bias Aware Probabilistic Boolean Matrix Factorization. 偏差感知概率布尔矩阵分解。

Proceedings of machine learning research Pub Date : 2022-08-01

Changlin Wan, Pengtao Dang, Tong Zhao, Yong Zang, Chi Zhang, Sha Cao

{"title":"Bias Aware Probabilistic Boolean Matrix Factorization.","authors":"Changlin Wan, Pengtao Dang, Tong Zhao, Yong Zang, Chi Zhang, Sha Cao","doi":"","DOIUrl":"","url":null,"abstract":"Boolean matrix factorization (BMF) is a combinatorial problem arising from a wide range of applications including recommendation system, collaborative filtering, and dimensionality reduction. Currently, the noise model of existing BMF methods is often assumed to be homoscedastic; however, in real world data scenarios, the deviations of observed data from their true values are almost surely diverse due to stochastic noises, making each data point not equally suitable for fitting a model. In this case, it is not ideal to treat all data points as equally distributed. Motivated by such observations, we introduce a probabilistic BMF model that recognizes the object- and feature-wise bias distribution respectively, called bias aware BMF (BABF). To the best of our knowledge, BABF is the first approach for Boolean decomposition with consideration of the feature-wise and object-wise bias in binary data. We conducted experiments on datasets with different levels of background noise, bias level, and sizes of the signal patterns, to test the effectiveness of our method in various scenarios. We demonstrated that our model outperforms the state-of-the-art factorization methods in both accuracy and efficiency in recovering the original datasets, and the inferred bias level is highly significantly correlated with true existing bias in both simulated and real world datasets.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"180 ","pages":"2035-2044"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10421704/pdf/nihms-1891928.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10060510","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

Survival Mixture Density Networks 生存混合密度网络

Proceedings of machine learning research Pub Date : 2022-08-01 DOI: 10.48550/arXiv.2208.10759

Xintian Han, Mark Goldstein, R. Ranganath

引用次数: 3

Few-Shot Learning with Semi-Supervised Transformers for Electronic Health Records. 用半监督变压器进行电子健康记录的短时间学习。

Proceedings of machine learning research Pub Date : 2022-08-01

Raphael Poulain, Mehak Gupta, Rahmatollah Beheshti

{"title":"Few-Shot Learning with Semi-Supervised Transformers for Electronic Health Records.","authors":"Raphael Poulain, Mehak Gupta, Rahmatollah Beheshti","doi":"","DOIUrl":"","url":null,"abstract":"With the growing availability of Electronic Health Records (EHRs), many deep learning methods have been developed to leverage such datasets in medical prediction tasks. Notably, transformer-based architectures have proven to be highly effective for EHRs. Transformer-based architectures are generally very effective in \"transferring\" the acquired knowledge from very large datasets to smaller target datasets through their comprehensive \"pre-training\" process. However, to work efficiently, they still rely on the target datasets for the downstream tasks, and if the target dataset is (very) small, the performance of downstream models can degrade rapidly. In biomedical applications, it is common to only have access to small datasets, for instance, when studying rare diseases, invasive procedures, or using restrictive cohort selection processes. In this study, we present CEHR-GAN-BERT, a semi-supervised transformer-based architecture that leverages both in- and out-of-cohort patients to learn better patient representations in the context of few-shot learning. The proposed method opens new learning opportunities where only a few hundred samples are available. We extensively evaluate our method on four prediction tasks and three public datasets showing the ability of our model to achieve improvements upwards of 5% on all performance metrics (including AUROC and F1 Score) on the tasks that use less than 200 annotated patients during the training process.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"182 ","pages":"853-873"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10399128/pdf/nihms-1865430.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9946062","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

Online Weak-form Sparse Identification of Partial Differential Equations. 偏微分方程的在线弱式稀疏识别。

Proceedings of machine learning research Pub Date : 2022-08-01

Daniel A Messenger, Emiliano Dall'anese, David M Bortz

{"title":"Online Weak-form Sparse Identification of Partial Differential Equations.","authors":"Daniel A Messenger, Emiliano Dall'anese, David M Bortz","doi":"","DOIUrl":"","url":null,"abstract":"This paper presents an online algorithm for identification of partial differential equations (PDEs) based on the weak-form sparse identification of nonlinear dynamics algorithm (WSINDy). The algorithm is online in the sense that if performs the identification task by processing solution snapshots that arrive sequentially. The core of the method combines a weak-form discretization of candidate PDEs with an online proximal gradient descent approach to the sparse regression problem. In particular, we do not regularize the <math><mrow><msub><mi>ℓ</mi><mn>0</mn></msub></mrow></math>-pseudo-norm, instead finding that directly applying its proximal operator (which corresponds to a hard thresholding) leads to efficient online system identification from noisy data. We demonstrate the success of the method on the Kuramoto-Sivashinsky equation, the nonlinear wave equation with time-varying wavespeed, and the linear wave equation, in one, two, and three spatial dimensions, respectively. In particular, our examples show that the method is capable of identifying and tracking systems with coefficients that vary abruptly in time, and offers a streaming alternative to problems in higher dimensions.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"190 ","pages":"241-256"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10805452/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139543114","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

Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning. 不同的审查和测试不足:临床机器学习中标签偏见的来源。

Proceedings of machine learning research Pub Date : 2022-08-01

Trenton Chang, Michael W Sjoding, Jenna Wiens

{"title":"Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning.","authors":"Trenton Chang, Michael W Sjoding, Jenna Wiens","doi":"","DOIUrl":"","url":null,"abstract":"As machine learning (ML) models gain traction in clinical applications, understanding the impact of clinician and societal biases on ML models is increasingly important. While biases can arise in the labels used for model training, the many sources from which these biases arise are not yet well-studied. In this paper, we highlight disparate censorship (i.e., differences in testing rates across patient groups) as a source of label bias that clinical ML models may amplify, potentially causing harm. Many patient risk-stratification models are trained using the results of clinician-ordered diagnostic and laboratory tests of labels. Patients without test results are often assigned a negative label, which assumes that untested patients do not experience the outcome. Since orders are affected by clinical and resource considerations, testing may not be uniform in patient populations, giving rise to disparate censorship. Disparate censorship in patients of equivalent risk leads to undertesting in certain groups, and in turn, more biased labels for such groups. Using such biased labels in standard ML pipelines could contribute to gaps in model performance across patient groups. Here, we theoretically and empirically characterize conditions in which disparate censorship or undertesting affect model performance across subgroups. Our findings call attention to disparate censorship as a source of label bias in clinical ML models.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"182 ","pages":"343-390"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10162497/pdf/nihms-1868579.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9437970","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

Survival Mixture Density Networks. 生存混合密度网络。

Proceedings of machine learning research Pub Date : 2022-08-01

Xintian Han, Mark Goldstein, Rajesh Ranganath

引用次数: 0

Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning 差异审查和测试不足：临床机器学习中标签偏见的来源

Proceedings of machine learning research Pub Date : 2022-08-01 DOI: 10.48550/arXiv.2208.01127

Trenton Chang, M. Sjoding, J. Wiens

{"title":"Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning","authors":"Trenton Chang, M. Sjoding, J. Wiens","doi":"10.48550/arXiv.2208.01127","DOIUrl":"https://doi.org/10.48550/arXiv.2208.01127","url":null,"abstract":"As machine learning (ML) models gain traction in clinical applications, understanding the impact of clinician and societal biases on ML models is increasingly important. While biases can arise in the labels used for model training, the many sources from which these biases arise are not yet well-studied. In this paper, we highlight disparate censorship (i.e., differences in testing rates across patient groups) as a source of label bias that clinical ML models may amplify, potentially causing harm. Many patient risk-stratification models are trained using the results of clinician-ordered diagnostic and laboratory tests of labels. Patients without test results are often assigned a negative label, which assumes that untested patients do not experience the outcome. Since orders are affected by clinical and resource considerations, testing may not be uniform in patient populations, giving rise to disparate censorship. Disparate censorship in patients of equivalent risk leads to undertesting in certain groups, and in turn, more biased labels for such groups. Using such biased labels in standard ML pipelines could contribute to gaps in model performance across patient groups. Here, we theoretically and empirically characterize conditions in which disparate censorship or undertesting affect model performance across subgroups. Our findings call attention to disparate censorship as a source of label bias in clinical ML models.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"182 1","pages":"343-390"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49527996","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: 6

Fair Generalized Linear Models with a Convex Penalty. 具有凹凸惩罚的公平广义线性模型

Proceedings of machine learning research Pub Date : 2022-07-01

Hyungrok Do, Preston Putzel, Axel Martin, Padhraic Smyth, Judy Zhong

引用次数: 0