Proceedings of machine learning research最新文献

筛选
英文 中文
From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions. 从有偏见的选择标签到伪标签:从有偏见的决策中学习的期望最大化框架。
Trenton Chang, Jenna Wiens
{"title":"From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisions.","authors":"Trenton Chang, Jenna Wiens","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Selective labels occur when label observations are subject to a decision-making process; <i>e.g</i>., diagnoses that depend on the administration of laboratory tests. We study a clinically-inspired selective label problem called disparate censorship, where labeling biases vary across subgroups and unlabeled individuals are imputed as \"negative\" (<i>i.e</i>., no diagnostic test = no illness). Machine learning models naïvely trained on such labels could amplify labeling bias. Inspired by causal models of selective labels, we propose Disparate Censorship Expectation-Maximization (DCEM), an algorithm for learning in the presence of disparate censorship. We theoretically analyze how DCEM mitigates the effects of disparate censorship on model performance. We validate DCEM on synthetic data, showing that it improves bias mitigation (area between ROC curves) without sacrificing discriminative performance (AUC) compared to baselines. We achieve similar results in a sepsis classification task using clinical data.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"235 ","pages":"6286-6324"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12199211/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144509908","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
Network conditioning for synergistic learning on partial annotations. 部分注释协同学习的网络调节。
Benjamin Billot, Neel Dey, Esra Abaci Turk, P Ellen Grant, Polina Golland
{"title":"Network conditioning for synergistic learning on partial annotations.","authors":"Benjamin Billot, Neel Dey, Esra Abaci Turk, P Ellen Grant, Polina Golland","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>The robustness and accuracy of multi-organ segmentation networks is limited by the scarcity of labels. A common strategy to alleviate the annotation burden is to use partially labelled datasets, where each image can be annotated for a subset of all organs of interest. Unfortunately, this approach causes inconsistencies in the background class since it can now include target organs. Moreover, we consider the even more relaxed setting of region-based segmentation, where voxels can be labelled for super-regions, thus causing further inconsistencies across annotations. Here we propose CoNeMOS (Conditional Network for Multi-Organ Segmentation), a framework that leverages a label-conditioned network for synergistic learning on partially labelled region-based segmentations. Conditioning is achieved by combining convolutions with expressive Feature-wise Linear Modulation (FiLM) layers, whose parameters are controlled by an auxiliary network. In contrast to other conditioning methods, FiLM layers are stable to train and add negligible computation overhead, which enables us to condition the entire network. As a result, the network can <i>learn</i> where it needs to extract shared or label-specific features, instead of imposing it with the architecture (e.g., with different segmentation heads). By encouraging flexible synergies across labels, our method obtains state-of-the-art results for the segmentation of challenging low-resolution fetal MRI data. Our code is available at https://github.com/BBillot/CoNeMOS.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"250 ","pages":"119-130"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12393823/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981797","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
Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability. 通过分布可学习性对分布转移下的可学习数据库操作进行理论分析》(Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability)。
Sepanta Zeighami, Cyrus Shahabi
{"title":"Theoretical Analysis of Learned Database Operations under Distribution Shift through Distribution Learnability.","authors":"Sepanta Zeighami, Cyrus Shahabi","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Use of machine learning to perform database operations, such as indexing, cardinality estimation, and sorting, is shown to provide substantial performance benefits. However, when datasets change and data distribution shifts, empirical results also show performance degradation for learned models, possibly to worse than non-learned alternatives. This, together with a lack of theoretical understanding of learned methods undermines their practical applicability, since there are no guarantees on how well the models will perform after deployment. In this paper, we present the first known theoretical characterization of the performance of learned models in dynamic datasets, for the aforementioned operations. Our results show novel theoretical characteristics achievable by learned models and provide bounds on the performance of the models that characterize their advantages over non-learned methods, showing why and when learned models can outperform the alternatives. Our analysis develops the <i>distribution learnability</i> framework and novel theoretical tools which build the foundation for the analysis of learned database operations in the future.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"235 ","pages":"58283-58305"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11534081/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577095","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
DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation. DISCRET:综合治疗效果估算的忠实解释。
Yinjun Wu, Mayank Keoliya, Kan Chen, Neelay Velingker, Ziyang Li, Emily J Getzen, Qi Long, Mayur Naik, Ravi B Parikh, Eric Wong
{"title":"DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation.","authors":"Yinjun Wu, Mayank Keoliya, Kan Chen, Neelay Velingker, Ziyang Li, Emily J Getzen, Qi Long, Mayur Naik, Ravi B Parikh, Eric Wong","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Designing faithful yet accurate AI models is challenging, particularly in the field of individual treatment effect estimation (ITE). ITE prediction models deployed in critical settings such as healthcare should ideally be (i) accurate, and (ii) provide faithful explanations. However, current solutions are inadequate: state-of-the-art black-box models do not supply explanations, post-hoc explainers for black-box models lack faithfulness guarantees, and self-interpretable models greatly compromise accuracy. To address these issues, we propose DISCRET, a self-interpretable ITE framework that synthesizes faithful, rule-based explanations for each sample. A key insight behind DISCRET is that explanations can serve dually as <i>database queries</i> to identify similar subgroups of samples. We provide a novel RL algorithm to efficiently synthesize these explanations from a large search space. We evaluate DISCRET on diverse tasks involving tabular, image, and text data. DISCRET outperforms the best self-interpretable models and has accuracy comparable to the best black-box models while providing faithful explanations. DISCRET is available at https://github.com/wuyinjun-1993/DISCRET-ICML2024.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"235 ","pages":"53597-53618"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11350397/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142115743","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
Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters. 核去偏插件估算:针对众多目标参数的无影响函数同步自动去差分。
Brian Cho, Yaroslav Mukhin, Kyra Gan, Ivana Malenica
{"title":"Kernel Debiased Plug-in Estimation: Simultaneous, Automated Debiasing without Influence Functions for Many Target Parameters.","authors":"Brian Cho, Yaroslav Mukhin, Kyra Gan, Ivana Malenica","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>When estimating target parameters in nonparametric models with nuisance parameters, substituting the unknown nuisances with nonparametric estimators can introduce \"plug-in bias.\" Traditional methods addressing this suboptimal bias-variance trade-off rely on the <i>influence function</i> (IF) of the target parameter. When estimating multiple target parameters, these methods require debiasing the nuisance parameter multiple times using the corresponding IFs, which poses analytical and computational challenges. In this work, we leverage the <i>targeted maximum likelihood estimation</i> (TMLE) framework to propose a novel method named <i>kernel debiased plug-in estimation</i> (KDPE). KDPE refines an initial estimate through regularized likelihood maximization steps, employing a nonparametric model based on <i>reproducing kernel Hilbert spaces</i>. We show that KDPE: (i) simultaneously debiases <i>all</i> pathwise differentiable target parameters that satisfy our regularity conditions, (ii) does not require the IF for implementation, and (iii) remains computationally tractable. We numerically illustrate the use of KDPE and validate our theoretical results.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"235 ","pages":"8534-8555"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11359899/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142115744","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
Position: Topological Deep Learning is the New Frontier for Relational Learning. 观点:拓扑深度学习是关系学习的新前沿。
Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi
{"title":"Position: Topological Deep Learning is the New Frontier for Relational Learning.","authors":"Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporating topological concepts, and can thus provide a natural choice for various machine learning settings. To this end, this paper discusses open problems in TDL, ranging from practical benefits to theoretical foundations. For each problem, it outlines potential solutions and future research opportunities. At the same time, this paper serves as an invitation to the scientific community to actively participate in TDL research to unlock the potential of this emerging field.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"235 ","pages":"39529-39555"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11973457/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143804858","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
Hidden Population Estimation with Indirect Inference and Auxiliary Information. 基于间接推断和辅助信息的隐藏总体估计。
Justin Weltz, Eric Laber, Alexander Volfovsky
{"title":"Hidden Population Estimation with Indirect Inference and Auxiliary Information.","authors":"Justin Weltz, Eric Laber, Alexander Volfovsky","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Many populations defined by illegal or stigmatized behavior are difficult to sample using conventional survey methodology. Respondent Driven Sampling (RDS) is a participant referral process frequently employed in this context to collect information. This sampling methodology can be modeled as a stochastic process that explores the graph of a social network, generating a partially observed subgraph between study participants. The methods currently used to impute the missing edges in this subgraph exhibit biased downstream estimation. We leverage auxiliary participant information and concepts from indirect inference to ameliorate these issues and improve estimation of the hidden population size. These advances result in smaller bias and higher precision in the estimation of the study participant arrival rate, the sample subgraph, and the population size. Lastly, we use our method to estimate the number of People Who Inject Drugs (PWID) in the Kohtla-Jarve region of Estonia.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"244 ","pages":"3730-3746"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12448677/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145115161","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
From Basic to Extra Features: Hypergraph Transformer Pretrain-then-Finetuning for Balanced Clinical Predictions on EHR. 从基本到额外的功能:超图变压器预训练-然后微调平衡临床预测电子病历。
Ran Xu, Yiwen Lu, Chang Liu, Yong Chen, Yan Sun, Xiao Hu, Joyce C Ho, Carl Yang
{"title":"From Basic to Extra Features: Hypergraph Transformer Pretrain-then-Finetuning for Balanced Clinical Predictions on EHR.","authors":"Ran Xu, Yiwen Lu, Chang Liu, Yong Chen, Yan Sun, Xiao Hu, Joyce C Ho, Carl Yang","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Electronic Health Records (EHRs) contain rich patient information and are crucial for clinical research and practice. In recent years, deep learning models have been applied to EHRs, but they often rely on massive features, which may not be readily available for all patients. We propose HTP-Star, which leverages hypergraph structures with a pretrain-then-finetune framework for modeling EHR data, enabling seamless integration of additional features. Additionally, we design two techniques, namely (1) <i>Smoothness-inducing Regularization</i> and (2) <i>Group-balanced Reweighting</i>, to enhance the model's robustness during finetuning. Through experiments conducted on two real EHR datasets, we demonstrate that HTP-Star consistently outperforms various baselines while striking a balance between patients with basic and extra features.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"248 ","pages":"182-197"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11876795/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560252","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
Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges. 利用 LLM 从电子病历中检索证据:可能性与挑战。
Hiba Ahsan, Denis Jered McInerney, Jisoo Kim, Christopher Potter, Geoffrey Young, Silvio Amir, Byron C Wallace
{"title":"Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges.","authors":"Hiba Ahsan, Denis Jered McInerney, Jisoo Kim, Christopher Potter, Geoffrey Young, Silvio Amir, Byron C Wallace","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Unstructured data in Electronic Health Records (EHRs) often contains critical information-complementary to imaging-that could inform radiologists' diagnoses. But the large volume of notes often associated with patients together with time constraints renders manually identifying relevant evidence practically infeasible. In this work we propose and evaluate a zero-shot strategy for using LLMs as a mechanism to efficiently retrieve and summarize unstructured evidence in patient EHR relevant to a given query. Our method entails tasking an LLM to infer whether a patient has, or is at risk of, a particular condition on the basis of associated notes; if so, we ask the model to summarize the supporting evidence. Under expert evaluation, we find that this LLM-based approach provides outputs consistently preferred to a pre-LLM information retrieval baseline. Manual evaluation is expensive, so we also propose and validate a method using an LLM to evaluate (other) LLM outputs for this task, allowing us to scale up evaluation. Our findings indicate the promise of LLMs as interfaces to EHR, but also highlight the outstanding challenge posed by \"hallucinations\". In this setting, however, we show that model confidence in outputs strongly correlates with faithful summaries, offering a practical means to limit confabulations.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"248 ","pages":"489-505"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11368037/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142121291","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
Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation. 用于体育锻炼数据估算的时空多尺度稀疏自我关注。
Hui Wei, Maxwell A Xu, Colin Samplawski, James M Rehg, Santosh Kumar, Benjamin M Marlin
{"title":"Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation.","authors":"Hui Wei, Maxwell A Xu, Colin Samplawski, James M Rehg, Santosh Kumar, Benjamin M Marlin","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Wearable sensors enable health researchers to continuously collect data pertaining to the physiological state of individuals in real-world settings. However, such data can be subject to extensive missingness due to a complex combination of factors. In this work, we study the problem of imputation of missing step count data, one of the most ubiquitous forms of wearable sensor data. We construct a novel and large scale data set consisting of a training set with over 3 million hourly step count observations and a test set with over 2.5 million hourly step count observations. We propose a domain knowledge-informed sparse self-attention model for this task that captures the temporal multi-scale nature of step-count data. We assess the performance of the model relative to baselines and conduct ablation studies to verify our specific model designs.</p>","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"248 ","pages":"137-154"},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11421853/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142334005","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信