Search Results for author:
Found 97 papers, 21 papers with code
Leveraging Registers in Vision Transformers for Robust Adaptation
To that end, we propose a simple method that combines the special CLS token embedding commonly employed in ViTs with the average-pooled register embeddings to create feature representations which are subsequently used for training a downstream classifier.
On The Role of Prompt Construction In Enhancing Efficacy and Efficiency of LLM-Based Tabular Data Generation
LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns.
DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation
Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation.
Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization
In this work, we investigate the fundamental trade-off regarding accuracy and parameter efficiency in the parameterization of neural network weights using predictor networks.
On the Use of Anchoring for Training Vision Models
Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities.
`Eyes of a Hawk and Ears of a Fox': Part Prototype Network for Generalized Zero-Shot Learning
Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector representation over the entire image.
Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
While graph neural networks (GNNs) are widely used for node and graph representation learning tasks, the reliability of GNN uncertainty estimates under distribution shifts remains relatively under-explored.
Transformer-Powered Surrogates Close the ICF Simulation-Experiment Gap with Extremely Limited Data
Recent advances in machine learning, specifically transformer architecture, have led to significant advancements in commercial domains.
Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Safe deployment of graph neural networks (GNNs) under distribution shift requires models to provide accurate confidence indicators (CI).
PAGER: A Framework for Failure Analysis of Deep Regression Models
Safe deployment of AI models requires proactive detection of failures to prevent costly errors.
CREPE: Learnable Prompting With CLIP Improves Visual Relationship Prediction
In this paper, we explore the potential of Vision-Language Models (VLMs), specifically CLIP, in predicting visual object relationships, which involves interpreting visual features from images into language-based relations.
Target-Aware Generative Augmentations for Single-Shot Adaptation
We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA, which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data.
On the Efficacy of Generalization Error Prediction Scoring Functions
Overall, our work carefully studies the effectiveness of popular scoring functions in realistic settings and helps to better understand their limitations.
A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
Advances in the expressivity of pretrained models have increased interest in the design of adaptation protocols which enable safe and effective transfer learning.
Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences between Pretrained Generative Models
To this end, we introduce Cross-GAN Auditing (xGA) that, given an established "reference" GAN and a newly proposed "client" GAN, jointly identifies intelligible attributes that are either common across both GANs, novel to the client GAN, or missing from the client GAN.
DOLCE: A Model-Based Probabilistic Diffusion Framework for Limited-Angle CT Reconstruction
Limited-Angle Computed Tomography (LACT) is a non-destructive evaluation technique used in a variety of applications ranging from security to medicine.
On-the-fly Object Detection using StyleGAN with CLIP Guidance
We present a fully automated framework for building object detectors on satellite imagery without requiring any human annotation or intervention.
Single-Shot Domain Adaptation via Target-Aware Generative Augmentation
The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks.
Analyzing Data-Centric Properties for Graph Contrastive Learning
Overall, our work rigorously contextualizes, both empirically and theoretically, the effects of data-centric properties on augmentation strategies and learning paradigms for graph SSL.
Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety
While directly fine-tuning (FT) large-scale, pretrained models on task-specific data is well-known to induce strong in-distribution task performance, recent works have demonstrated that different adaptation protocols, such as linear probing (LP) prior to FT, can improve out-of-distribution generalization.
Contrastive Knowledge-Augmented Meta-Learning for Few-Shot Classification
Model agnostic meta-learning algorithms aim to infer priors from several observed tasks that can then be used to adapt to a new task with few examples.
Single Model Uncertainty Estimation via Stochastic Data Centering
We are interested in estimating the uncertainties of deep neural networks, which play an important role in many scientific and engineering problems.
Know Your Space: Inlier and Outlier Construction for Calibrating Medical OOD Detectors
We focus on the problem of producing well-calibrated out-of-distribution (OOD) detectors, in order to enable safe deployment of medical image classifiers.
Domain Alignment Meets Fully Test-Time Adaptation
With a minimal overhead of storing the subspace basis set for the source data, CATTAn enables unsupervised alignment between source and target data during adaptation.
Out of Distribution Detection via Neural Network Anchoring
Our goal in this paper is to exploit heteroscedastic temperature scaling as a calibration strategy for out of distribution (OOD) detection.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Improving Diversity with Adversarially Learned Transformations for Domain Generalization
To be successful in single source domain generalization, maximizing diversity of synthesized domains has emerged as one of the most effective strategies.
Automated Domain Discovery from Multiple Sources to Improve Zero-Shot Generalization
In this paper, we focus on the challenging problem of multi-source zero shot DG (MDG), where labeled training data from multiple source domains is available but with no access to data from the target domain.
Ranked #27 on
Domain Generalization
on TerraIncognita
Geometric Priors for Scientific Generative Models in Inertial Confinement Fusion
In this paper, we develop a Wasserstein autoencoder (WAE) with a hyperspherical prior for multimodal data in the application of inertial confinement fusion.
$Δ$-UQ: Accurate Uncertainty Quantification via Anchor Marginalization
Anchoring works by first transforming the input into a tuple consisting of an anchor point drawn from a prior distribution, and a combination of the input sample with the anchor using a pretext encoding scheme.
A Biology-Informed Similarity Metric for Simulated Patches of Human Cell Membrane
Complex scientific inquiries rely increasingly upon large and autonomous multiscale simulation campaigns, which fundamentally require similarity metrics to quantify "sufficient'' changes among data and/or configurations.
Designing Counterfactual Generators using Deep Model Inversion
Explanation techniques that synthesize small, interpretable changes to a given image while producing desired changes in the model prediction have become popular for introspecting black-box models.
MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation
Medical AI has tremendous potential to advance healthcare by supporting the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving provider and patient experience.
Interrogating Paradigms in Self-supervised Graph Representation Learning
Using the recent population augmentation graph-based analysis of self-supervised learning, we show theoretically that the success of GCL with popular augmentations is bounded by the graph edit distance between different classes.
Suppressing simulation bias using multi-modal data
The method described in this paper can be applied to a wide range of problems that require transferring knowledge from simulations to the domain of experiments.
On the Design of Deep Priors for Unsupervised Audio Restoration
Unsupervised deep learning methods for solving audio restoration problems extensively rely on carefully tailored neural architectures that carry strong inductive biases for defining priors in the time or spectral domain.
Loss Estimators Improve Model Generalization
With increased interest in adopting AI methods for clinical diagnosis, a vital step towards safe deployment of such tools is to ensure that the models not only produce accurate predictions but also do not generalize to data regimes where the training data provide no meaningful evidence.
Comparative Code Structure Analysis using Deep Learning for Performance Prediction
Performance analysis has always been an afterthought during the application development process, focusing on application correctness first.
Attribute-Guided Adversarial Training for Robustness to Natural Perturbations
While this deviation may not be exactly known, its broad characterization is specified a priori, in terms of attributes.
A Statistical Mechanics Framework for Task-Agnostic Sample Design in Machine Learning
Using this framework, we show that space-filling sample designs, such as blue noise and Poisson disk sampling, which optimize spectral properties, outperform random designs in terms of the generalization gap and characterize this gain in a closed-form.
Meaningful uncertainties from deep neural network surrogates of large-scale numerical simulations
Large-scale numerical simulations are used across many scientific disciplines to facilitate experimental development and provide insights into underlying physical processes, but they come with a significant computational cost.
Using Deep Image Priors to Generate Counterfactual Explanations
Through the use of carefully tailored convolutional neural network architectures, a deep image prior (DIP) can be used to obtain pre-images from latent representation encodings.
Machine Learning-Powered Mitigation Policy Optimization in Epidemiological Models
A crucial aspect of managing a public health crisis is to effectively balance prevention and mitigation strategies, while taking their socio-economic impact into account.
Accurate Calibration of Agent-based Epidemiological Models with Neural Network Surrogates
Here we present a new approach to calibrate an agent-based model -- EpiCast -- using a large set of simulation ensembles for different major metropolitan areas of the United States.
Ask-n-Learn: Active Learning via Reliable Gradient Representations for Image Classification
Deep predictive models rely on human supervision in the form of labeled training data.
Accurate and Robust Feature Importance Estimation under Distribution Shifts
With increasing reliance on the outcomes of black-box models in critical applications, post-hoc explainability tools that do not require access to the model internals are often used to enable humans understand and trust these models.
Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks
In this work, we propose Uncertainty Matching GNN (UM-GNN), that is aimed at improving the robustness of GNN models, particularly against poisoning attacks to the graph structure, by leveraging epistemic uncertainties from the message passing framework.
Unsupervised Audio Source Separation using Generative Priors
State-of-the-art under-determined audio source separation systems rely on supervised end-end training of carefully tailored neural network architectures operating either in the time or the spectral domain.
Designing Accurate Emulators for Scientific Processes using Calibration-Driven Deep Models
Predictive models that accurately emulate complex scientific processes can achieve exponential speed-ups over numerical simulators or experiments, and at the same time provide surrogates for improving the subsequent analysis.
Self-Training with Improved Regularization for Sample-Efficient Chest X-Ray Classification
Automated diagnostic assistants in healthcare necessitate accurate AI models that can be trained with limited labeled data, can cope with severe class imbalances and can support simultaneous prediction of multiple disease conditions.
Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models
The wide-spread adoption of representation learning technologies in clinical decision making strongly emphasizes the need for characterizing model reliability and enabling rigorous introspection of model behavior.
Calibrate and Prune: Improving Reliability of Lottery Tickets Through Prediction Calibration
The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generalizable models, has led to crucial insights into network initialization and has enabled efficient inferencing.
Improved Surrogates in Inertial Confinement Fusion with Manifold and Cycle Consistencies
Neural networks have become very popular in surrogate modeling because of their ability to characterize arbitrary, high dimensional functions in a data driven fashion.
MimicGAN: Robust Projection onto Image Manifolds with Corruption Mimicking
However, PGD is a brittle optimization technique that fails to identify the right projection (or latent vector) when the observation is corrupted, or perturbed even by a small amount.
Invenio: Discovering Hidden Relationships Between Tasks/Domains Using Structured Meta Learning
Exploiting known semantic relationships between fine-grained tasks is critical to the success of recent model agnostic approaches.
Heteroscedastic Calibration of Uncertainty Estimators in Deep Learning
The role of uncertainty quantification (UQ) in deep learning has become crucial with growing use of predictive models in high-risk applications.
Learn-By-Calibrating: Using Calibration as a Training Objective
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks.
Exploring Generative Physics Models with Scientific Priors in Inertial Confinement Fusion
There is significant interest in using modern neural networks for scientific applications due to their effectiveness in modeling highly complex, non-linear problems in a data-driven fashion.
Improving Limited Angle CT Reconstruction with a Robust GAN Prior
Limited angle CT reconstruction is an under-determined linear inverse problem that requires appropriate regularization techniques to be solved.
Function Preserving Projection for Scalable Exploration of High-Dimensional Data
We present function preserving projections (FPP), a scalable linear projection technique for discovering interpretable relationships in high-dimensional data.
Building Calibrated Deep Models via Uncertainty Matching with Auxiliary Interval Predictors
With rapid adoption of deep learning in critical applications, the question of when and how much to trust these models often arises, which drives the need to quantify the inherent uncertainties.
Distill-to-Label: Weakly Supervised Instance Labeling Using Knowledge Distillation
Weakly supervised instance labeling using only image-level labels, in lieu of expensive fine-grained pixel annotations, is crucial in several applications including medical image analysis.
Scalable Topological Data Analysis and Visualization for Evaluating Data-Driven Models in Scientific Applications
With the rapid adoption of machine learning techniques for large-scale applications in science and engineering comes the convergence of two grand challenges in visualization.
SALT: Subspace Alignment as an Auxiliary Learning Task for Domain Adaptation
This paper represents a hybrid approach, where we assume simplified data geometry in the form of subspaces, and consider alignment as an auxiliary task to the primary task of maximizing performance on the source.
A Look at the Effect of Sample Design on Generalization through the Lens of Spectral Analysis
This paper provides a general framework to study the effect of sampling properties of training data on the generalization error of the learned machine learning (ML) models.
Audio Source Separation via Multi-Scale Learning with Dilated Dense U-Nets
We also investigate the impact of dense connections on the extraction process that encourage feature reuse and better gradient flow.
MimicGAN: Corruption-Mimicking for Blind Image Recovery & Adversarial Defense
Solving inverse problems continues to be a central challenge in computer vision.
Multiple Subspace Alignment Improves Domain Adaptation
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition.
Designing an Effective Metric Learning Pipeline for Speaker Diarization
State-of-the-art speaker diarization systems utilize knowledge from external data, in the form of a pre-trained distance metric, to effectively determine relative speaker identities to unseen data.
A Regularized Attention Mechanism for Graph Attention Networks
Machine learning models that can exploit the inherent structure in data have gained prominence.
Understanding Deep Neural Networks through Input Uncertainties
Techniques for understanding the functioning of complex machine learning models are becoming increasingly popular, not only to improve the validation process, but also to extract new insights about the data via exploratory analysis.
Unsupervised Dimension Selection using a Blue Noise Spectrum
Unsupervised dimension selection is an important problem that seeks to reduce dimensionality of data, while preserving the most useful characteristics.
Attention Models with Random Features for Multi-layered Graph Embeddings
Though deep network embeddings, e. g. DeepWalk, are widely adopted for community discovery, we argue that feature learning with random node attributes, using graph neural networks, can be more effective.
Understanding Behavior of Clinical Models under Domain Shifts
The hypothesis that computational models can be reliable enough to be adopted in prognosis and patient care is revolutionizing healthcare.
Improved Deep Embeddings for Inferencing with Multi-Layered Networks
Inferencing with network data necessitates the mapping of its nodes into a vector space, where the relationships are preserved.
Coverage-Based Designs Improve Sample Mining and Hyper-Parameter Optimization
Sampling one or more effective solutions from large search spaces is a recurring idea in machine learning, and sequential optimization has become a popular solution.
Triplet Network with Attention for Speaker Diarization
In automatic speech processing systems, speaker diarization is a crucial front-end component to separate segments from different speakers.
An Unsupervised Approach to Solving Inverse Problems using Generative Adversarial Networks
We solve this by making successive estimates on the model and the solution in an iterative fashion.
A Generative Modeling Approach to Limited Channel ECG Classification
Processing temporal sequences is central to a variety of applications in health care, and in particular multi-channel Electrocardiogram (ECG) is a highly prevalent diagnostic modality that relies on robust sequence modeling.
Exploring High-Dimensional Structure via Axis-Aligned Decomposition of Linear Projections
Furthermore, we introduce a new approach to discover a diverse set of high quality linear projections and show that in practice the information of $k$ linear projections is often jointly encoded in $\sim k$ axis aligned plots.
A Spectral Approach for the Design of Experiments: Design, Analysis and Algorithms
Third, we propose an efficient estimator to evaluate the space-filling properties of sample designs in arbitrary dimensions and use it to develop an optimization framework to generate high quality space-filling designs.
Lose The Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion
The classical techniques require measuring projections, called sinograms, from a full 180$^\circ$ view of the object.
MARGIN: Uncovering Deep Neural Networks using Graph Signal Analysis
Interpretability has emerged as a crucial aspect of building trust in machine learning systems, aimed at providing insights into the working of complex neural networks that are otherwise opaque to a user.
Optimizing Kernel Machines using Deep Learning
To this end, we develop the DKMO (Deep Kernel Machine Optimization) framework, that creates an ensemble of dense embeddings using Nystrom kernel approximations and utilizes deep learning to generate task-specific representations through the fusion of the embeddings.
Attend and Diagnose: Clinical Time Series Analysis using Attention Models
With widespread adoption of electronic health records, there is an increased emphasis for predictive models that can effectively deal with clinical time-series data.
Bootstrapping Graph Convolutional Neural Networks for Autism Spectrum Disorder Classification
To address this, we propose a bootstrapped version of graph convolutional neural networks (G-CNNs) that utilizes an ensemble of weakly trained G-CNNs, and reduce the sensitivity of models on the choice of graph construction.
A Deep Learning Approach To Multiple Kernel Fusion
Kernel fusion is a popular and effective approach for combining multiple features that characterize different aspects of data.
Robust Local Scaling using Conditional Quantiles of Graph Similarities
In this paper, we propose the use of quantile analysis to obtain local scale estimates for neighborhood graph construction.
Influential Node Detection in Implicit Social Networks using Multi-task Gaussian Copula Models
Influential node detection is a central research topic in social network analysis.
Autism Spectrum Disorder Classification using Graph Kernels on Multidimensional Time Series
We present an approach to model time series data from resting state fMRI for autism spectrum disorder (ASD) severity classification.
TreeView: Peeking into Deep Neural Networks Via Feature-Space Partitioning
In this paper, we take a step in the direction of tackling the problem of interpretability without compromising the model accuracy.
Universal Collaboration Strategies for Signal Detection: A Sparse Learning Approach
This paper considers the problem of high dimensional signal detection in a large distributed network whose nodes can collaborate with their one-hop neighboring nodes (spatial collaboration).
Automatic Inference of the Quantile Parameter
However, loss functions such as quantile and quantile Huber generalize the symmetric $\ell_1$ and Huber losses to the asymmetric setting, for a fixed quantile parameter.
Beyond L2-Loss Functions for Learning Sparse Models
We propose an algorithm to learn dictionaries and obtain sparse codes when the data reconstruction fidelity is measured using any smooth PLQ cost function.
Recovering Non-negative and Combined Sparse Representations
For case (c), we propose the combined orthogonal matching pursuit algorithm for coefficient recovery and derive the deterministic sparsity threshold under which recovery of the unique, sparsest coefficient vector is possible.
Learning Stable Multilevel Dictionaries for Sparse Representations
Algorithmic stability and generalization are desirable characteristics for dictionary learning algorithms that aim to build global dictionaries which can efficiently model any test data similar to the training samples.
Multiple Kernel Sparse Representations for Supervised and Unsupervised Learning
Descriptors that have diverse forms can be fused into a unified feature space in a principled manner using kernel methods.
