Search Results for author:
Found 59 papers, 14 papers with code
AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Bias
Such architectural design and abstractions enable researchers and developers to extend the toolkit with their new algorithms and improvements, and to use it for performance benchmarking.
The Impact of Positional Encoding on Length Generalization in Transformers
In this paper, we conduct a systematic empirical study comparing the length generalization performance of decoder-only Transformers with five different position encoding approaches including Absolute Position Embedding (APE), T5's Relative PE, ALiBi, and Rotary, in addition to Transformers without positional encoding (NoPE).
Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI
In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models.
Topological Deep Learning: Going Beyond Graph Data
Topological deep learning is a rapidly growing field that pertains to the development of deep learning models for data supported on topological domains such as simplicial complexes, cell complexes, and hypergraphs, which generalize many domains encountered in scientific computations.
ICML 2023 Topological Deep Learning Challenge : Design and Results
This paper presents the computational challenge on topological deep learning that was hosted within the ICML 2023 Workshop on Topology and Geometry in Machine Learning.
TopoX: A Suite of Python Packages for Machine Learning on Topological Domains
We introduce TopoX, a Python software suite that provides reliable and user-friendly building blocks for computing and machine learning on topological domains that extend graphs: hypergraphs, simplicial, cellular, path and combinatorial complexes.
Bridging Mode Connectivity in Loss Landscapes and Adversarial Robustness
In this work, we propose to employ mode connectivity in loss landscapes to study the adversarial robustness of deep neural networks, and provide novel methods for improving this robustness.
Topological Data Analysis of Decision Boundaries with Application to Model Selection
We propose the labeled \v{C}ech complex, the plain labeled Vietoris-Rips complex, and the locally scaled labeled Vietoris-Rips complex to perform persistent homology inference of decision boundaries in classification tasks.
PI-Net: A Deep Learning Approach to Extract Topological Persistence Images
To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data.
Optimized Data Pre-Processing for Discrimination Prevention
Non-discrimination is a recognized objective in algorithmic decision making.
Perturbation Robust Representations of Topological Persistence Diagrams
However, persistence diagrams are multi-sets of points and hence it is not straightforward to fuse them with features used for contemporary machine learning tools like deep-nets.
A Riemannian Framework for Statistical Analysis of Topological Persistence Diagrams
This paper concerns itself with one popular topological feature, which is the number of $d-$dimensional holes in the dataset, also known as the Betti$-d$ number.
Finding the Homology of Decision Boundaries with Active Learning
We theoretically analyze the proposed framework and show that the query complexity of our active learning algorithm depends naturally on the intrinsic complexity of the underlying manifold.
Teaching Meaningful Explanations
The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate responsibility for decisions and outcomes.
Simultaneous Parameter Learning and Bi-Clustering for Multi-Response Models
We consider multi-response and multitask regression models, where the parameter matrix to be estimated is expected to have an unknown grouping structure.
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.
Distribution-Preserving k-Anonymity
Preserving the privacy of individuals by protecting their sensitive attributes is an important consideration during microdata release.
Multitask Learning using Task Clustering with Applications to Predictive Modeling and GWAS of Plant Varieties
Inferring predictive maps between multiple input and multiple output variables or tasks has innumerable applications in data science.
Distributed Bundle Adjustment
The runtime of our implementation scales linearly with the number of observed points.
Learning Robust Representations for Computer Vision
Unsupervised learning techniques in computer vision often require learning latent representations, such as low-dimensional linear and non-linear subspaces.
Estimating Shape Parameters of Piecewise Linear-Quadratic Problems
The normalization constant inherent in this requirement helps to inform the optimization over shape parameters, giving a joint optimization problem over these as well as primary parameters of interest.
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.
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.
Persistent Homology of Attractors For Action Recognition
In this paper, we propose a novel framework for dynamical analysis of human actions from 3D motion capture data using topological data analysis.
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.
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.
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.
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.
FactSheets: Increasing Trust in AI Services through Supplier's Declarations of Conformity
We envision such documents to contain purpose, performance, safety, security, and provenance information to be completed by AI service providers for examination by consumers.
TED: Teaching AI to Explain its Decisions
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions.
Bias Mitigation Post-processing for Individual and Group Fairness
Whereas previous post-processing approaches for increasing the fairness of predictions of biased classifiers address only group fairness, we propose a method for increasing both individual and group fairness.
Optimized Pre-Processing for Discrimination Prevention
Non-discrimination is a recognized objective in algorithmic decision making.
Adaptive As-Natural-As-Possible Image Stitching
Computing the warp is fully automated and uses a combination of local homography and global similarity transformations, both of which are estimated with respect to the target.
Crowd Counting with Decomposed Uncertainty
Uncertainty quantification accompanied by point estimation can lead to a more informed decision, and even improve the prediction quality.
Counting and Segmenting Sorghum Heads
We also propose a novel instance segmentation algorithm using the estimated density map, to identify the individual panicles in the presence of occlusion.
Optimized Score Transformation for Consistent Fair Classification
We derive a closed-form expression for the optimal transformed scores and a convex optimization problem for the transformation parameters.
Teaching AI to Explain its Decisions Using Embeddings and Multi-Task Learning
Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility for decisions and outcomes.
Understanding racial bias in health using the Medical Expenditure Panel Survey data
Over the years, several studies have demonstrated that there exist significant disparities in health indicators in the United States population across various groups.
Drug Repurposing for Cancer: An NLP Approach to Identify Low-Cost Therapies
More than 200 generic drugs approved by the U. S. Food and Drug Administration for non-cancer indications have shown promise for treating cancer.
Model Agnostic Multilevel Explanations
The method can also leverage side information, where users can specify points for which they may want the explanations to be similar.
Characterizing the Latent Space of Molecular Deep Generative Models with Persistent Homology Metrics
In this work, we propose a method for measuring how well the latent space of deep generative models is able to encode structural and chemical features of molecular datasets by correlating latent space metrics with metrics from the field of topological data analysis (TDA).
Augmenting Molecular Deep Generative Models with Topological Data Analysis Representations
Deep generative models have emerged as a powerful tool for learning useful molecular representations and designing novel molecules with desired properties, with applications in drug discovery and material design.
Your fairness may vary: Pretrained language model fairness in toxic text classification
Through the analysis of more than a dozen pretrained language models of varying sizes on two toxic text classification tasks (English), we demonstrate that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics.
Data-Centric AI Requires Rethinking Data Notion
The transition towards data-centric AI requires revisiting data notions from mathematical and implementational standpoints to obtain unified data-centric machine learning packages.
Locally Invariant Explanations: Towards Causal Explanations through Local Invariant Learning
Locally interpretable model agnostic explanations (LIME) method is one of the most popular methods used to explain black-box models at a per example level.
A label-efficient two-sample test
Two-sample tests evaluate whether two samples are realizations of the same distribution (the null hypothesis) or two different distributions (the alternative hypothesis).
Comparing Fisher Information Regularization with Distillation for DNN Quantization
A large body of work addresses deep neural network (DNN) quantization and pruning to mitigate the high computational burden of deploying DNNs.
Ground-Truth, Whose Truth? -- Examining the Challenges with Annotating Toxic Text Datasets
The use of machine learning (ML)-based language models (LMs) to monitor content online is on the rise.
Analogies and Feature Attributions for Model Agnostic Explanation of Similarity Learners
We first propose a method that provides feature attributions to explain the similarity between a pair of inputs as determined by a black box similarity learner.
Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models
We also provide a novel group-theoretic definition for fairness in NLG.
Active Sequential Two-Sample Testing
The classification model is adaptively updated and then used to guide an active query scheme called bimodal query to label sample features in the regions with high dependency between the feature variables and the label variables.
Function Composition in Trustworthy Machine Learning: Implementation Choices, Insights, and Questions
In this paper, focusing specifically on compositions of functions arising from the different pillars, we aim to reduce this gap, develop new insights for trustworthy ML, and answer questions such as the following.
Topo-MLP : A Simplicial Network Without Message Passing
To overcome such limitations, we propose Topo-MLP, a purely MLP-based simplicial neural network algorithm to learn the representation of elements in a simplicial complex without explicitly relying on message passing.
Position Paper: Challenges and Opportunities in Topological Deep Learning
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models.
Trust Regions for Explanations via Black-Box Probabilistic Certification
fidelity, stability), can we find the largest hypercube (i. e., $\ell_{\infty}$ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz.
Ranking Large Language Models without Ground Truth
and a set of LLMs, we rank them without access to any ground truth or reference responses.
Multi-Level Explanations for Generative Language Models
To address the challenges of text as output and long text inputs, we propose a general framework called MExGen that can be instantiated with different attribution algorithms.
