Search Results for author:
Found 19 papers, 3 papers with code
REFRESH: Responsible and Efficient Feature Reselection Guided by SHAP Values
In this paper, we introduce the problem of feature \emph{reselection}, so that features can be selected with respect to secondary model performance characteristics efficiently even after a feature selection process has been done with respect to a primary objective.
Demystifying Local and Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
This work presents an information-theoretic perspective to group fairness trade-offs in federated learning (FL) with respect to sensitive attributes, such as gender, race, etc.
Robust Counterfactual Explanations for Neural Networks With Probabilistic Guarantees
There is an emerging interest in generating robust counterfactual explanations that would remain valid if the model is updated or changed even slightly.
Hyper-parameter Tuning for Fair Classification without Sensitive Attribute Access
Recent work has sought to train fair models without sensitive attributes on training data.
Can Querying for Bias Leak Protected Attributes? Achieving Privacy With Smooth Sensitivity
In this paper, we first demonstrate that simply querying for fairness metrics, such as statistical parity and equalized odds can leak the protected attributes of individuals to the model developers.
Robust Counterfactual Explanations for Tree-Based Ensembles
In this work, we propose a novel strategy -- that we call RobX -- to generate robust counterfactuals for tree-based ensembles, e. g., XGBoost.
Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale
We further show that MinDiff optimization is very sensitive to choice of batch size in the under-parameterized regime.
Quantifying Feature Contributions to Overall Disparity Using Information Theory
If we have access to the decision-making model, one potential approach (inspired from intervention-based approaches in explainability literature) is to vary each individual feature (while keeping the others fixed) and use the resulting change in disparity to quantify its contribution.
Can Information Flows Suggest Targets for Interventions in Neural Circuits?
Motivated by neuroscientific and clinical applications, we empirically examine whether observational measures of information flow can suggest interventions.
A Survey on the Robustness of Feature Importance and Counterfactual Explanations
There exist several methods that aim to address the crucial task of understanding the behaviour of AI/ML models.
GTN-ED: Event Detection Using Graph Transformer Networks
Recent works show that the graph structure of sentences, generated from dependency parsers, has potential for improving event detection.
Fairness Under Feature Exemptions: Counterfactual and Observational Measures
While quantifying disparity is essential, sometimes the needs of an occupation may require the use of certain features that are critical in a way that any disparity that can be explained by them might need to be exempted.
Slow and Stale Gradients Can Win the Race
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in runtime as it waits for the slowest workers (stragglers).
Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing
Moreover, the same classifier yields the lack of a trade-off with respect to ideal distributions while yielding a trade-off when accuracy is measured with respect to the given (possibly biased) dataset.
CodeNet: Training Large Scale Neural Networks in Presence of Soft-Errors
This work proposes the first strategy to make distributed training of neural networks resilient to computing errors, a problem that has remained unsolved despite being first posed in 1956 by von Neumann.
A Unified Coded Deep Neural Network Training Strategy Based on Generalized PolyDot Codes for Matrix Multiplication
First, we propose a novel coded matrix multiplication technique called Generalized PolyDot codes that advances on existing methods for coded matrix multiplication under storage and communication constraints.
Slow and Stale Gradients Can Win the Race: Error-Runtime Trade-offs in Distributed SGD
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in waiting for the slowest learners (stragglers).
On the Optimal Recovery Threshold of Coded Matrix Multiplication
We provide novel coded computation strategies for distributed matrix-matrix products that outperform the recent "Polynomial code" constructions in recovery threshold, i. e., the required number of successful workers.
Information Theory Distributed, Parallel, and Cluster Computing Information Theory
Short-Dot: Computing Large Linear Transforms Distributedly Using Coded Short Dot Products
The fusion node can exploit this redundancy by completing the computation using outputs from only a subset of the processors, ignoring the stragglers.
