Search Results for author:
Found 30 papers, 10 papers with code
A Primal-Dual Framework for Transformers and Neural Networks
Self-attention is key to the remarkable success of transformers in sequence modeling tasks including many applications in natural language processing and computer vision.
AutoKG: Efficient Automated Knowledge Graph Generation for Language Models
Traditional methods of linking large language models (LLMs) to knowledge bases via the semantic similarity search often fall short of capturing complex relational dynamics.
Novel Batch Active Learning Approach and Its Application to Synthetic Aperture Radar Datasets
Active learning improves the performance of machine learning methods by judiciously selecting a limited number of unlabeled data points to query for labels, with the aim of maximally improving the underlying classifier's performance.
Graph-based Active Learning for Surface Water and Sediment Detection in Multispectral Images
We develop a graph active learning pipeline (GAP) to detect surface water and in-river sediment pixels in satellite images.
Proximal Implicit ODE Solvers for Accelerating Learning Neural ODEs
Learning neural ODEs often requires solving very stiff ODE systems, primarily using explicit adaptive step size ODE solvers.
Graph-based Active Learning for Semi-supervised Classification of SAR Data
We use a Convolutional Neural Network Variational Autoencoder (CNNVAE) to embed SAR data into a feature space, and then construct a similarity graph from the embedded data and apply graph-based semi-supervised learning techniques.
Efficient and Reliable Overlay Networks for Decentralized Federated Learning
As such, our proposed overlay networks accelerate convergence, improve generalization, and enhance robustness to clients failures in DFL with theoretical guarantees.
Model-Change Active Learning in Graph-Based Semi-Supervised Learning
Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.
Heavy Ball Neural Ordinary Differential Equations
We propose heavy ball neural ordinary differential equations (HBNODEs), leveraging the continuous limit of the classical momentum accelerated gradient descent, to improve neural ODEs (NODEs) training and inference.
An Analysis of COVID-19 Knowledge Graph Construction and Applications
The construction and application of knowledge graphs have seen a rapid increase across many disciplines in recent years.
Post-Radiotherapy PET Image Outcome Prediction by Deep Learning under Biological Model Guidance: A Feasibility Study of Oropharyngeal Cancer Application
With break-down biological modeling components, the outcome image predictions could be used in adaptive radiotherapy decision-making to optimize personalized plans for the best outcome in the future.
Posterior Consistency of Semi-Supervised Regression on Graphs
Graph-based semi-supervised regression (SSR) is the problem of estimating the value of a function on a weighted graph from its values (labels) on a small subset of the vertices.
Efficient Graph-Based Active Learning with Probit Likelihood via Gaussian Approximations
We present a novel adaptation of active learning to graph-based semi-supervised learning (SSL) under non-Gaussian Bayesian models.
MomentumRNN: Integrating Momentum into Recurrent Neural Networks
Designing deep neural networks is an art that often involves an expensive search over candidate architectures.
Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities
To bridge this gap, we introduce a declustering based hidden variable model that leads to an efficient inference procedure via a variational autoencoder (VAE).
Sparsity Meets Robustness: Channel Pruning for the Feynman-Kac Formalism Principled Robust Deep Neural Nets
In this paper, we focus on a co-design of efficient DNN compression algorithms and sparse neural architectures for robust and accurate deep learning.
Scheduled Restart Momentum for Accelerated Stochastic Gradient Descent
Nesterov accelerated gradient (NAG) improves the convergence rate of gradient descent (GD) for convex optimization using a specially designed momentum; however, it accumulates error when an inexact gradient is used (such as in SGD), slowing convergence at best and diverging at worst.
Semi-Supervised First-Person Activity Recognition in Body-Worn Video
Body-worn cameras are now commonly used for logging daily life, sports, and law enforcement activities, creating a large volume of archived footage.
A Study on Graph-Structured Recurrent Neural Networks and Sparsification with Application to Epidemic Forecasting
We study epidemic forecasting on real-world health data by a graph-structured recurrent neural network (GSRNN).
Multivariate Spatiotemporal Hawkes Processes and Network Reconstruction
There is often latent network structure in spatial and temporal data and the tools of network analysis can yield fascinating insights into such data.
Adversarial Defense via Data Dependent Activation Function and Total Variation Minimization
We improve the robustness of Deep Neural Net (DNN) to adversarial attacks by using an interpolating function as the output activation.
Stochastic Block Models are a Discrete Surface Tension
Networks, which represent agents and interactions between them, arise in myriad applications throughout the sciences, engineering, and even the humanities.
Graph-Based Deep Modeling and Real Time Forecasting of Sparse Spatio-Temporal Data
We present a generic framework for spatio-temporal (ST) data modeling, analysis, and forecasting, with a special focus on data that is sparse in both space and time.
Deep Learning for Real-Time Crime Forecasting and its Ternarization
In this work, we first present a proper representation of crime data.
Simplified Energy Landscape for Modularity Using Total Variation
We show that modularity optimization is equivalent to minimizing a convex TV-based functional over a discrete domain, again, assuming the number of communities is known.
Deep Learning for Real Time Crime Forecasting
Experiments over a half year period in Los Angeles reveal highly accurate predictive power of our models.
Uncertainty quantification in graph-based classification of high dimensional data
In this paper we introduce, develop algorithms for, and investigate the properties of, a variety of Bayesian models for the task of binary classification; via the posterior distribution on the classification labels, these methods automatically give measures of uncertainty.
Unsupervised Classification in Hyperspectral Imagery with Nonlocal Total Variation and Primal-Dual Hybrid Gradient Algorithm
In this paper, a graph-based nonlocal total variation method (NLTV) is proposed for unsupervised classification of hyperspectral images (HSI).
Multiclass Data Segmentation using Diffuse Interface Methods on Graphs
We present two graph-based algorithms for multiclass segmentation of high-dimensional data.
