Related papers: Probabilistic Feature Imputation and Uncertainty-A…

Pathology image segmentation across multiple centers encounters significant challenges due to diverse sources of heterogeneity including imaging modalities, organs, and scanning equipment, whose variability brings representation bias and…

Federated learning enables distributed clients to collaborate on training while storing their data locally to protect client privacy. However, due to the heterogeneity of data, models, and devices, the final global model may need to perform…

Federated learning encounters substantial challenges with heterogeneous data, leading to performance degradation and convergence issues. While considerable progress has been achieved in mitigating such an impact, the reliability aspect of…

Multimodal learning has seen great success mining data features from multiple modalities with remarkable model performance improvement. Meanwhile, federated learning (FL) addresses the data sharing problem, enabling privacy-preserved…

Medical image segmentation plays a crucial role in AI-assisted diagnostics, surgical planning, and treatment monitoring. Accurate and robust segmentation models are essential for enabling reliable, data-driven clinical decision making…

Medical decision-making requires integrating diverse medical information, from imaging to clinical narratives. These medical modalities are often acquired in a many-to-many manner. However, current medical vision-language pretraining models…

Electronic health records (EHR) consist of longitudinal clinical observations portrayed with sparsity, irregularity, and high-dimensionality, which become major obstacles in drawing reliable downstream clinical outcomes. Although there…

Federated Learning enables multiple data centers to train a central model collaboratively without exposing any confidential data. Even though deterministic models are capable of performing high prediction accuracy, their lack of calibration…

A fundamental challenge in federated learning lies in mixing heterogeneous datasets and classification tasks while minimizing the high communication cost caused by clients as well as the exchange of weight updates with the server over a…

Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs) by embedding physical laws directly into neural network training. However, solving high-fidelity PDEs remains…

Acquiring pixel-level annotations is often limited in applications such as histology studies that require domain expertise. Various semi-supervised learning approaches have been developed to work with limited ground truth annotations, such…

As artificial intelligence systems increasingly operate in Real-world environments, the integration of multi-modal data sources such as vision, language, and audio presents both unprecedented opportunities and critical challenges for…

Multimodal Federated Learning (MMFL) utilizes multiple modalities in each client to build a more powerful Federated Learning (FL) model than its unimodal counterpart. However, the impact of missing modality in different clients, also called…

Federated learning is a very convenient approach for scenarios where (i) the exchange of data implies privacy concerns and/or (ii) a quick reaction is needed. In smart healthcare systems, both aspects are usually required. In this paper, we…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…

Deep neural networks has been increasingly applied in fault diagnostics, where it uses historical data to capture systems behavior, bypassing the need for high-fidelity physical models. However, despite their competence in prediction tasks,…

Federated learning (FL) is a decentralized machine learning paradigm in which multiple clients collaboratively train a shared model without sharing their local private data. However, real-world applications of FL frequently encounter…

Real-world problems are often dependent on multiple data modalities, making multimodal fusion essential for leveraging diverse information sources. In high-stakes domains, such as in healthcare, understanding how each modality contributes…

Uncertainty quantification (UQ) in scientific machine learning is increasingly critical as neural networks are widely adopted to tackle complex problems across diverse scientific disciplines. For physics-informed neural networks (PINNs), a…

Although multi-view unsupervised feature selection (MUFS) is an effective technology for reducing dimensionality in machine learning, existing methods cannot directly deal with incomplete multi-view data where some samples are missing in…