DeepAI AI Chat
Log In Sign Up

Robust Attribution Regularization

by   Jiefeng Chen, et al.

An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatically attributing a neural network's output change to its input change. We propose training objectives in classic robust optimization models to achieve robust IG attributions. Our objectives give principled generalizations of previous objectives designed for robust predictions, and they naturally degenerate to classic soft-margin training for one-layer neural networks. We also generalize previous theory and prove that the objectives for different robust optimization models are closely related. Experiments demonstrate the effectiveness of our method, and also point to intriguing problems which hint at the need for better optimization techniques or better neural network architectures for robust attribution training.


page 2

page 19

page 20

page 21


Four Axiomatic Characterizations of the Integrated Gradients Attribution Method

Deep neural networks have produced significant progress among machine le...

FAR: A General Framework for Attributional Robustness

Attribution maps have gained popularity as tools for explaining neural n...

Enhanced Regularizers for Attributional Robustness

Deep neural networks are the default choice of learning models for compu...

On the Benefits of Attributional Robustness

Interpretability is an emerging area of research in trustworthy machine ...

Attribution-based Explanations that Provide Recourse Cannot be Robust

Different users of machine learning methods require different explanatio...

Towards More Robust Interpretation via Local Gradient Alignment

Neural network interpretation methods, particularly feature attribution ...

Attribution Preservation in Network Compression for Reliable Network Interpretation

Neural networks embedded in safety-sensitive applications such as self-d...

Code Repositories


Robust Attribution Regularization

view repo