Concept-Based Explanations for Tabular Data

09/13/2022
by   Varsha Pendyala, et al.
University of Wisconsin-Madison
0

The interpretability of machine learning models has been an essential area of research for the safe deployment of machine learning systems. One particular approach is to attribute model decisions to high-level concepts that humans can understand. However, such concept-based explainability for Deep Neural Networks (DNNs) has been studied mostly on image domain. In this paper, we extend TCAV, the concept attribution approach, to tabular learning, by providing an idea on how to define concepts over tabular data. On a synthetic dataset with ground-truth concept explanations and a real-world dataset, we show the validity of our method in generating interpretability results that match the human-level intuitions. On top of this, we propose a notion of fairness based on TCAV that quantifies what layer of DNN has learned representations that lead to biased predictions of the model. Also, we empirically demonstrate the relation of TCAV-based fairness to a group fairness notion, Demographic Parity.

READ FULL TEXT
10/17/2019

On Concept-Based Explanations in Deep Neural Networks

Deep neural networks (DNNs) build high-level intelligence on low-level r...
02/25/2022

Human-Centered Concept Explanations for Neural Networks

Understanding complex machine learning models such as deep neural networ...
02/07/2019

Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks

Interpretability has become an important topic of research as more machi...
05/03/2023

Explaining Language Models' Predictions with High-Impact Concepts

The emergence of large-scale pretrained language models has posed unprec...
03/04/2022

Concept-based Explanations for Out-Of-Distribution Detectors

Out-of-distribution (OOD) detection plays a crucial role in ensuring the...
01/25/2023

Towards Robust Metrics for Concept Representation Evaluation

Recent work on interpretability has focused on concept-based explanation...
07/01/2020

Unifying Model Explainability and Robustness via Machine-Checkable Concepts

As deep neural networks (DNNs) get adopted in an ever-increasing number ...

Please sign up or login with your details

Forgot password? Click here to reset