most citedExplanations of Black-Box Models based on Directional Feature Interactions

9 citations · 9 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2023

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Max Torop, Aria Masoomi, Davin Hill +3

Several recent methods for interpretability model feature interactions by looking at the Hessian of a neural network. This poses a challenge for ReLU networks, which are piecewise-…

cs.LG20239 cited

Explanations of Black-Box Models based on Directional Feature Interactions

Aria Masoomi, Davin Hill, Zhonghui Xu +5

As machine learning algorithms are deployed ubiquitously to a variety of domains, it is imperative to make these often black-box models transparent. Several recent works explain bl…

cs.LG2023

Geometry of Score Based Generative Models

Sandesh Ghimire, Jinyang Liu, Armand Comas +4

In this work, we look at Score-based generative models (also called diffusion generative models) from a geometric perspective. From a new view point, we prove that both the forward…

cs.CV2023

Divide and Compose with Score Based Generative Models

Sandesh Ghimire, Armand Comas, Davin Hill +3

While score based generative models, or diffusion models, have found success in image synthesis, they are often coupled with text data or image label to be able to manipulate and c…

cs.LG2022

Inv-SENnet: Invariant Self Expression Network for clustering under biased data

Ashutosh Singh, Ashish Singh, Aria Masoomi +3

Subspace clustering algorithms are used for understanding the cluster structure that explains the dataset well. These methods are extensively used for data-exploration tasks in var…