Skip to search formSkip to main contentSkip to account menu

Improving performance of deep learning models with axiomatic attribution priors and expected gradients

This work introduces an explanation method, called ‘expected gradients’, that enables training with theoretically motivated feature attribution priors, to improve model performance on real-world tasks.
Springer Nature (opens in a new tab)

Visualizing the Impact of Feature Attribution Baselines

Publisher (opens in a new tab)

Explaining Explanations: Axiomatic Feature Interactions for Deep Networks

This work presents Integrated Hessians, an extension of Integrated Gradients that explains pairwise feature interactions in neural networks and finds that the method is faster than existing methods when the number of features is large, and outperforms previous methods on existing quantitative benchmarks.
arXiv (opens in a new tab)

Learning Explainable Models Using Attribution Priors

A differentiable axiomatic feature attribution method called expected gradients is developed and shown how to directly regularize these attributions during training and produce models with more intuitive behavior and better generalization performance by encoding constraints that would otherwise be very difficult to encode using standard model priors.
arXiv (opens in a new tab)

FoggySight: A Scheme for Facial Lookup Privacy

FoggySight is proposed and evaluated, a solution that applies lessons learned from the adversarial examples literature to modify facial photos in a privacy-preserving manner before they are uploaded to social media and it is found that it does enable protection of facial privacy – including against a facial recognition service with unknown internals.
arXiv (opens in a new tab)

Profile Prediction: An Alignment-Based Pre-Training Task for Protein Sequence Models

This work introduces a new pre-training task: directly predicting protein profiles derived from multiple sequence alignments that outperforms masked language modeling alone on all five tasks and suggests that protein sequence models may benefit from leveraging biologically-inspired inductive biases that go beyond existing language modeling techniques in NLP.
arXiv (opens in a new tab)

Automated Brain Masking of Fetal Functional MRI with Open Data

This work solves the most challenging processing step, rapid and accurate isolation of the fetal brain from surrounding tissue across thousands of non-stationary 3D brain volumes and unifies the auto-masking model with additional fMRI preprocessing steps from existing software and provides insight into the adaptation of each step.
Springer Nature (opens in a new tab)

The Lair: a resource for exploratory analysis of published RNA-Seq data

A series of tools for processing and analyzing RNA-Seq data in the Sequence Read Archive are introduced, that together have allowed us to build an easily extendable resource for analysis of data underlying published papers.
Springer Nature (opens in a new tab)

Select and Permute: An Improved Online Framework for Scheduling to Minimize Weighted Completion Time

This framework uses two offline approximation algorithms—one for the simpler problem of scheduling without release times, and another for the minimum unscheduled weight problem—to create an online algorithm with provably good competitive ratios.
arXiv (opens in a new tab)

A Domain Guided CNN Architecture for Predicting Age from Structural Brain Images

The results suggest that lessons learned from developing models on natural images may not directly transfer to neuroimaging tasks, and there remains a large space of unexplored questions regarding model development in this area.
arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)