Search Results for author:
Found 7 papers, 3 papers with code
Using Captum to Explain Generative Language Models
Captum is a comprehensive library for model explainability in PyTorch, offering a range of methods from the interpretability literature to enhance users' understanding of PyTorch models.
Bias Mitigation Framework for Intersectional Subgroups in Neural Networks
We propose a fairness-aware learning framework that mitigates intersectional subgroup bias associated with protected attributes.
Convolutional Networks are Inherently Foveated
When convolutional layers apply no padding, central pixels have more ways to contribute to the convolution than peripheral pixels.
Investigating sanity checks for saliency maps with image and text classification
Saliency maps have shown to be both useful and misleading for explaining model predictions especially in the context of images.
Investigating Saturation Effects in Integrated Gradients
We explore these effects and find that gradients in saturated regions of this path, where model output changes minimally, contribute disproportionately to the computed attribution.
Mind the Pad -- CNNs can Develop Blind Spots
We show how feature maps in convolutional networks are susceptible to spatial bias.
Captum: A unified and generic model interpretability library for PyTorch
The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms, also known as feature, neuron and layer importance algorithms, as well as a set of evaluation metrics for these algorithms.
