Search Results for author:
Found 9 papers, 6 papers with code
TaCo: Targeted Concept Removal in Output Embeddings for NLP via Information Theory and Explainability
In evaluation, we show that the proposed post-hoc approach significantly reduces gender-related associations in NLP models while preserving the overall performance and functionality of the models.
Improved learning theory for kernel distribution regression with two-stage sampling
In this paper, we improve the learning theory of kernel distribution regression.
Gaussian Processes on Distributions based on Regularized Optimal Transport
We present a novel kernel over the space of probability measures based on the dual formulation of optimal regularized transport.
On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective
Input gradients have a pivotal role in a variety of applications, including adversarial attack algorithms for evaluating model robustness, explainable AI techniques for generating Saliency Maps, and counterfactual explanations. However, Saliency Maps generated by traditional neural networks are often noisy and provide limited insights.
GAN Estimation of Lipschitz Optimal Transport Maps
This paper introduces the first statistically consistent estimator of the optimal transport map between two probability distributions, based on neural networks.
Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks
However they remain commonly considered as less accurate, and their properties in learning are still not fully understood.
Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs
Measuring the generalization performance of a Deep Neural Network (DNN) without relying on a validation set is a difficult task.
Predicting the Accuracy of a Few-Shot Classifier
In the context of few-shot learning, one cannot measure the generalization ability of a trained classifier using validation sets, due to the small number of labeled samples.
Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening
We propose a novel algorithm for unsupervised graph representation learning with attributed graphs.
