Robust and Stable Black Box Explanations
Jul 12, 2020
Speakers
Nino Arsov
Speaker · 0 followers
Osbert Bastani
Speaker · 0 followers
Hima Lakkaraju
Speaker · 1 follower
About
As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black box models. However, existing algorithms for generating such explanations have been shown to lack robustness with respect to shifts in the underlying data distribution. In this paper, we propose a novel framework for generating robust explanations of black box models based on adversarial training. In particular, our framework optimizes a minimax objective that aims to construct the highest fidelity explanation with respect to the worst-case over a set of distribution shifts. We instantiate this algorithm for explanations in the form of linear models and decision sets by devising the required optimization procedures. To the best of our knowledge, this work makes the first attempt at generating post hoc explanations that are robust to a general class of distribution shifts that are of practical interest. Experimental evaluation with real-world and synthetic datasets demonstrates that our approach substantially improves the robustness of explanations without sacrificing their fidelity on the original data distribution.As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black box models. However, existing algorithms for generating such explanations have been shown to lack robustness with respect to shifts in the underlying data distribution. In this paper, we propose a novel framework for generating robust explanations of black box models based on adversarial train…
Categories
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Pseudo-Masked Language Models for Unified Language Model Pre-Training
Watch later
Hangbo Bao, …
Differentiable Product Quantization for Learning Compact Embedding Layers
Watch later
Ting Chen, …
Stochastic Gradient and Langevin Processes
Watch later
Xiang Cheng, …
Decentralised Learning with Random Features and Distributed Gradient Descent
Watch later
NGBoost: Natural Gradient Boosting for Probabilistic Prediction
Watch later
Tony Duan, …
Exploring Robust Optimization via Adversarial Influence Functions (AIF)
Watch later
Zhun Deng, …