Proceedings of machine learning research最新文献_第3页

Structure-informed Risk Minimization for Robust Ensemble Learning. 基于结构的鲁棒集成学习风险最小化。

Proceedings of machine learning research Pub Date : 2025-07-01

Fengchun Qiao, Yanlin Chen, Xi Peng

{"title":"Structure-informed Risk Minimization for Robust Ensemble Learning.","authors":"Fengchun Qiao, Yanlin Chen, Xi Peng","doi":"","DOIUrl":"","url":null,"abstract":"Ensemble learning is a powerful approach for improving generalization under distribution shifts, but its effectiveness heavily depends on how individual models are combined. Existing methods often optimize ensemble weights based on validation data, which may not represent unseen test distributions, leading to suboptimal performance in out-of-distribution (OoD) settings. Inspired by Distributionally Robust Optimization (DRO), we propose Structure-informed Risk Minimization (SRM), a principled framework that learns robust ensemble weights without access to test data. Unlike standard DRO, which defines uncertainty sets based on divergence metrics alone, SRM incorporates structural information of training distributions, ensuring that the uncertainty set aligns with plausible real-world shifts. This approach mitigates the over-pessimism of traditional worst-case optimization while maintaining robustness. We introduce a computationally efficient optimization algorithm with theoretical guarantees and demonstrate that SRM achieves superior OoD generalization compared to existing ensemble combination strategies across diverse benchmarks. Code is available at: https://github.com/deep-real/SRM.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"267 ","pages":"50130-50141"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13131038/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147824469","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

Accurate Identification of Communication Between Multiple Interacting Neural Populations. 多个相互作用的神经群体之间通信的准确识别。

Proceedings of machine learning research Pub Date : 2025-07-01

Belle Liu, Jacob Sacks, Matthew D Golub

引用次数: 0

Confounder-Free Continual Learning via Recursive Feature Normalization. 通过递归特征归一化的无混杂持续学习。

Proceedings of machine learning research Pub Date : 2025-07-01

Yash Shah, Camila Gonzalez, Mohammad H Abbasi, Qingyu Zhao, Kilian M Pohl, Ehsan Adeli

{"title":"Confounder-Free Continual Learning via Recursive Feature Normalization.","authors":"Yash Shah, Camila Gonzalez, Mohammad H Abbasi, Qingyu Zhao, Kilian M Pohl, Ehsan Adeli","doi":"","DOIUrl":"","url":null,"abstract":"Confounders are extraneous variables that affect both the input and the target, resulting in spurious correlations and biased predictions. There are recent advances in dealing with or removing confounders in traditional models, such as metadata normalization (MDN), where the distribution of the learned features is adjusted based on the study confounders. However, in the context of continual learning, where a model learns continuously from new data over time without forgetting, learning feature representations that are invariant to confounders remains a significant challenge. To remove their influence from intermediate feature representations, we introduce the Recursive MDN (R-MDN) layer, which can be integrated into any deep learning architecture, including vision transformers, and at any model stage. R-MDN performs statistical regression via the recursive least squares algorithm to maintain and continually update an internal model state with respect to changing distributions of data and confounding variables. Our experiments demonstrate that R-MDN promotes equitable predictions across population groups, both within static learning and across different stages of continual learning, by reducing catastrophic forgetting caused by confounder effects changing over time.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"267 ","pages":"54112-54142"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12823023/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146032030","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

Active Feature Acquisition Via Explainability-driven Ranking. 通过可解释性驱动排名获取主动功能。

Proceedings of machine learning research Pub Date : 2025-07-01

Osman Berke Guney, Ketan Suhaas Saichandran, Karim Elzokm, Ziming Zhang, Vijaya B Kolachalama

{"title":"Active Feature Acquisition Via Explainability-driven Ranking.","authors":"Osman Berke Guney, Ketan Suhaas Saichandran, Karim Elzokm, Ziming Zhang, Vijaya B Kolachalama","doi":"","DOIUrl":"","url":null,"abstract":"In many practical applications, including medicine, acquiring all relevant data for machine learning models is often infeasible due to constraints on time, cost, and resources. This makes it important to selectively acquire only the most informative features, yet traditional static feature selection methods fall short in scenarios where feature importance varies across instances. Here, we propose an active feature acquisition (AFA) framework, which dynamically selects features based on their importance to each individual case. Our method leverages local explanation techniques to generate instance-specific feature importance rankings. We then reframe the AFA problem as a feature prediction task, introducing a policy network grounded in a decision transformer architecture. This policy network is trained to select the next most informative feature by learning from the feature importance rankings. As a result, features are acquired sequentially, ordered by their predictive significance, leading to more efficient feature selection and acquisition. Extensive experiments on multiple datasets demonstrate that our approach outperforms current state-of-the-art AFA methods in predictive accuracy and feature acquisition efficiency. These findings highlight the promise of an explainability-driven AFA strategy in scenarios where feature acquisition is a concern.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"267 ","pages":"20748-20765"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12661659/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145650405","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

Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery. 神经可解释偏微分方程：协调傅立叶见解与注意可扩展和可解释的物理发现。

Proceedings of machine learning research Pub Date : 2025-07-01

Ning Liu, Yue Yu

{"title":"Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery.","authors":"Ning Liu, Yue Yu","doi":"","DOIUrl":"","url":null,"abstract":"Attention mechanisms have emerged as transformative tools in core AI domains such as natural language processing and computer vision. Yet, their largely untapped potential for modeling intricate physical systems presents a compelling frontier. Learning such systems often entails discovering operators that map between functional spaces using limited instances of function pairs-a task commonly framed as a severely ill-posed inverse PDE problem. In this work, we introduce Neural Interpretable PDEs (NIPS), a novel neural operator architecture that builds upon and enhances Nonlocal Attention Operators (NAO) in both predictive accuracy and computational efficiency. NIPS employs a linear attention mechanism to enable scalable learning and integrates a learnable kernel network that acts as a channel-independent convolution in Fourier space. As a consequence, NIPS eliminates the need to explicitly compute and store large pairwise interactions, effectively amortizing the cost of handling spatial interactions into the Fourier transform. Empirical evaluations demonstrate that NIPS consistently surpasses NAO and other baselines across diverse benchmarks, heralding a substantial leap in scalable, interpretable, and efficient physics learning. Our code and data accompanying this paper are available at https://github.com/fishmoon1234/Nonlocal-Attention-Operator.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"267 ","pages":"40085-40099"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12981550/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147470090","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 Diffusion Duality. 扩散二象性。

Proceedings of machine learning research Pub Date : 2025-07-01

Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin Chiu, Volodymyr Kuleshov

引用次数: 0

Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications. Poly2Vec: GeoAI应用中地理空间对象的多态傅立叶编码。

Proceedings of machine learning research Pub Date : 2025-07-01

Maria Despoina Siampou, Jialiang Li, John Krumm, Cyrus Shahabi, Hua Lu

{"title":"Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications.","authors":"Maria Despoina Siampou, Jialiang Li, John Krumm, Cyrus Shahabi, Hua Lu","doi":"","DOIUrl":"","url":null,"abstract":"Encoding geospatial objects is fundamental for geospatial artificial intelligence (GeoAI) applications, which leverage machine learning (ML) models to analyze spatial information. Common approaches transform each object into known formats, like image and text, for compatibility with ML models. However, this process often discards crucial spatial information, such as the object's position relative to the entire space, reducing downstream task effectiveness. Alternative encoding methods that preserve some spatial properties are often devised for specific data objects (e.g., point encoders), making them unsuitable for tasks that involve different data types (i.e., points, polylines, and polygons). To this end, we propose Poly2Vec, a polymorphic Fourier-based encoding approach that unifies the representation of geospatial objects, while preserving the essential spatial properties. Poly2Vec incorporates a learned fusion module that adaptively integrates the magnitude and phase of the Fourier transform for different tasks and geometries. We evaluate Poly2Vec on five diverse tasks, organized into two categories. The first empirically demonstrates that Poly2Vec consistently outperforms object-specific baselines in preserving three key spatial relationships: topology, direction, and distance. The second shows that integrating Poly2Vec into a state-of-the-art GeoAI workflow improves the performance in two popular tasks: population prediction and land use inference.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"267 ","pages":"55511-55532"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13078377/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147693992","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

Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference. 利用层次贝叶斯推理的异构统计强度进行个性化联邦学习。

Proceedings of machine learning research Pub Date : 2025-07-01

Mahendra Singh Thapa, Rui Li

{"title":"Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference.","authors":"Mahendra Singh Thapa, Rui Li","doi":"","DOIUrl":"","url":null,"abstract":"Personalized federated learning (PFL) based on Bayesian approach tackle the challenges from statistical heterogeneity of client data by computing a personalized posterior distribution over the parameters of each client's local model and constructing a global distribution by aggregating the parameters of these personalized posteriors. However, the heuristic aggregation methods introduce strong biases and result in global models with poor generalization. We thus propose a novel hierarchical Bayesian inference framework for PFL by specifying a conjugate hyper-prior over the parameters of the personalized posteriors. This allows us to jointly compute a global posterior distribution for aggregation and the personalized ones at local level. This hierarchical Bayesian inference framework achieves elegant balance between local personalization and global model robustness. Extensive empirical study shows that by effectively sharing the heterogeneous statistical strength across the local models while retaining their distinctive characteristics, our framework yields state-of-the-art performance. We also show that existing Bayesian PFLs are special cases of our framework.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"267 ","pages":"59285-59303"},"PeriodicalIF":0.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13050239/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147624937","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 Impact of Medication Non-adherence on Adverse Outcomes: Evidence from Schizophrenia Patients via Survival Analysis. 药物不依从性对不良结局的影响：来自精神分裂症患者生存分析的证据。

Proceedings of machine learning research Pub Date : 2025-06-01

Shahriar Noroozizadeh, Pim Welle, Jeremy C Weiss, George H Chen

{"title":"The Impact of Medication Non-adherence on Adverse Outcomes: Evidence from Schizophrenia Patients via Survival Analysis.","authors":"Shahriar Noroozizadeh, Pim Welle, Jeremy C Weiss, George H Chen","doi":"","DOIUrl":"","url":null,"abstract":"This study quantifies the association between non-adherence to antipsychotic medications and adverse outcomes in individuals with schizophrenia. We frame the problem using survival analysis, focusing on the time to the earliest of several adverse events (early death, involuntary hospitalization, jail booking). We extend standard causal inference methods (T-learner, S-learner, nearest neighbor matching) to utilize various survival models to estimate individual and average treatment effects, where treatment corresponds to medication non-adherence. Analyses are repeated using different amounts of longitudinal information (3, 6, 9, and 12 months). Using data from Allegheny County in western Pennsylvania, we find strong evidence that non-adherence advances adverse outcomes by approximately 1 to 4 months. Ablation studies confirm that county-provided risk scores adjust for key confounders, as their removal amplifies the estimated effects. Subgroup analyses by medication formulation (injectable vs. oral) and medication type consistently show that non-adherence is associated with earlier adverse events. These findings highlight the clinical importance of adherence in delaying psychiatric crises and show that integrating survival analysis with causal inference tools can yield policy-relevant insights. We caution that although we apply causal inference, we only make associative claims and discuss assumptions needed for causal interpretation.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"287 ","pages":"573-609"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12444782/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145115155","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

Benchmarking Missing Data Imputation Methods for Time Series Using Real-World Test Cases. 使用真实世界测试用例对时间序列的缺失数据插入方法进行基准测试。

Proceedings of machine learning research Pub Date : 2025-06-01

Adedolapo Aishat Toye, Asuman Celik, Samantha Kleinberg

{"title":"Benchmarking Missing Data Imputation Methods for Time Series Using Real-World Test Cases.","authors":"Adedolapo Aishat Toye, Asuman Celik, Samantha Kleinberg","doi":"","DOIUrl":"","url":null,"abstract":"Missing data is pervasive in healthcare. Many imputation methods exist to fill in missing values, yet most were evaluated using randomly deleted values rather than the actual mechanisms they were designed to address. We aimed to determine real-world accuracy for missing data imputation with three missing data mechanisms (missing completely at random, MCAR; missing at random, MAR; and not missing at random, NMAR) for state of the art and commonly used imputation methods. Using two time series data targets (continuous glucose monitoring, Loop dataset; heart rate, All of Us dataset) we simulated missingness by masking values for each mechanism, at a range of missingness percentages (5-30%) and tested 12 imputation methods. We evaluated accuracy with multiple metrics including root mean square error (RMSE) and bias. We found that overall, accuracy was significantly better on MCAR than on MAR and NMAR, despite many methods being developed for those mechanisms. Linear interpolation had the lowest RMSE with all mechanisms and for all demographic groups, with low bias. This study shows that current evaluation practices do not provide an accurate picture of real world performance with realistic patterns of missingness. Future research is needed to develop evaluation practices that better capture real-world accuracy, and methods that better address real-world mechanisms.","PeriodicalId":74504,"journal":{"name":"Proceedings of machine learning research","volume":"287 ","pages":"480-501"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12392262/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144981808","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