29 citations · 91 across the 48 of their papers we have counts for
23 papers · 1 filter
When Confidence Lacks Concepts: Interpretable OOD Detection via Representation Perturbations
Anju Chhetri, Pratik Shrestha, Ramesh Rana +3
Deep neural networks have achieved remarkable performance across medical imaging tasks, yet their tendency to overgeneralize under distributional shifts poses a major obstacle to s…
BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation
Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Gyawali +2
High-Dimensional Low-Sample Size (HDLSS) tabular domains (e.g., omics) are characterized by , where = number of samples, and = number of features. Such domains oft…
GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data
Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Kumar Gyawali +2
We investigate how to make small tabular foundation models effective for High-Dimensional, Low-Sample Size (HDLSS) tabular prediction without retraining large backbones. We introdu…
Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
Shourov Joarder, Diganta Sikdar, Ahsan Habib Akash +2
Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of LLMs, but often depends on external supervision from human annotations or…
Investigating Trustworthiness of Nonparametric Deep Survival Models for Alzheimer's Disease Progression Analysis
Jacob Thrasher, Kaitlyn Heintzelman, Peter Martone +4
Alzheimer's Dementia (AD) is a progressive neurodegenerative disease marked by irreversible decline, making reliable modeling of its progression essential for effective patient car…
FedVG: Gradient-Guided Aggregation for Enhanced Federated Learning
Alina Devkota, Jacob Thrasher, Donald Adjeroh +2
Federated Learning (FL) enables collaborative model training across multiple clients without sharing their private data. However, data heterogeneity across clients leads to client…
Local K-Similarity Constraint for Federated Learning with Label Noise
Sanskar Amgain, Prashant Shrestha, Bidur Khanal +5
Federated learning on clients with noisy labels is a challenging problem, as such clients can infiltrate the global model, impacting the overall generalizability of the system. Exi…
Multimodal Federated Learning With Missing Modalities through Feature Imputation Network
Pranav Poudel, Aavash Chhetri, Prashnna Gyawali +2
Multimodal federated learning holds immense potential for collaboratively training models from multiple sources without sharing raw data, addressing both data scarcity and privacy…
Supervised Pretraining for Material Property Prediction
Chowdhury Mohammad Abid Rahman, Aldo H. Romero, Prashnna K. Gyawali
Accurate prediction of material properties facilitates the discovery of novel materials with tailored functionalities. Deep learning models have recently shown superior accuracy an…
Enhancing material property prediction with ensemble deep graph convolutional networks
Chowdhury Mohammad Abid Rahman, Ghadendra Bhandari, Nasser M Nasrabadi +2
Machine learning (ML) models have emerged as powerful tools for accelerating materials discovery and design by enabling accurate predictions of properties from compositional and st…
Multimodal Federated Learning in Healthcare: a Review
Jacob Thrasher, Alina Devkota, Prasiddha Siwakotai +5
Recent advancements in multimodal machine learning have empowered the development of accurate and robust AI systems in the medical domain, especially within centralized database sy…
Ensembling improves stability and power of feature selection for deep learning models
Prashnna K Gyawali, Xiaoxia Liu, James Zou +1
With the growing adoption of deep learning models in different real-world domains, including computational biology, it is often necessary to understand which data features are esse…
Improving genetic risk prediction across diverse population by disentangling ancestry representations
Prashnna K Gyawali, Yann Le Guen, Xiaoxia Liu +3
Risk prediction models using genetic data have seen increasing traction in genomics. However, most of the polygenic risk models were developed using data from participants with sim…
Enhancing Mixup-based Semi-Supervised Learning with Explicit Lipschitz Regularization
Prashnna Kumar Gyawali, Sandesh Ghimire, Linwei Wang
The success of deep learning relies on the availability of large-scale annotated data sets, the acquisition of which can be costly, requiring expert domain knowledge. Semi-supervis…
Semi-supervised Medical Image Classification with Global Latent Mixing
Prashnna Kumar Gyawali, Sandesh Ghimire, Pradeep Bajracharya +2
Computer-aided diagnosis via deep learning relies on large-scale annotated data sets, which can be costly when involving expert knowledge. Semi-supervised learning (SSL) mitigates…
Progressive Learning and Disentanglement of Hierarchical Representations
Zhiyuan Li, Jaideep Vitthal Murkute, Prashnna Kumar Gyawali +1
Learning rich representation from data is an important task for deep generative models such as variational auto-encoder (VAE). However, by extracting high-level abstractions in the…
Analysis of Discriminator in RKHS Function Space for Kullback-Leibler Divergence Estimation
Sandesh Ghimire, Prashnna K Gyawali, Linwei Wang
Several scalable sample-based methods to compute the Kullback Leibler (KL) divergence between two distributions have been proposed and applied in large-scale machine learning model…
Improving Disentangled Representation Learning with the Beta Bernoulli Process
Prashnna Kumar Gyawali, Zhiyuan Li, Cameron Knight +4
To improve the ability of VAE to disentangle in the latent space, existing works mostly focus on enforcing independence among the learned latent factors. However, the ability of th…
Semi-Supervised Learning by Disentangling and Self-Ensembling Over Stochastic Latent Space
Prashnna Kumar Gyawali, Zhiyuan Li, Sandesh Ghimire +1
The success of deep learning in medical imaging is mostly achieved at the cost of a large labeled data set. Semi-supervised learning (SSL) provides a promising solution by leveragi…
Improving Generalization of Deep Networks for Inverse Reconstruction of Image Sequences
Sandesh Ghimire, Prashnna Kumar Gyawali, Jwala Dhamala +3
Deep learning networks have shown state-of-the-art performance in many image reconstruction problems. However, it is not well understood what properties of representation and learn…
Deep Generative Model with Beta Bernoulli Process for Modeling and Learning Confounding Factors
Prashnna K Gyawali, Cameron Knight, Sandesh Ghimire +3
While deep representation learning has become increasingly capable of separating task-relevant representations from other confounding factors in the data, two significant challenge…
Improving Generalization of Sequence Encoder-Decoder Networks for Inverse Imaging of Cardiac Transmembrane Potential
Sandesh Ghimire, Prashnna Kumar Gyawali, John L Sapp +2
Deep learning models have shown state-of-the-art performance in many inverse reconstruction problems. However, it is not well understood what properties of the latent representatio…
Learning disentangled representation from 12-lead electrograms: application in localizing the origin of Ventricular Tachycardia
Prashnna K Gyawali, B. Milan Horacek, John L. Sapp +1
The increasing availability of electrocardiogram (ECG) data has motivated the use of data-driven models for automating various clinical tasks based on ECG data. The development of…