MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks

04/16/2021
by   Danilo Numeroso, et al.
0

Explainable AI (XAI) is a research area whose objective is to increase trustworthiness and to enlighten the hidden mechanism of opaque machine learning techniques. This becomes increasingly important in case such models are applied to the chemistry domain, for its potential impact on humans' health, e.g, toxicity analysis in pharmacology. In this paper, we present a novel approach to tackle explainability of deep graph networks in the context of molecule property prediction t asks, named MEG (Molecular Explanation Generator). We generate informative counterfactual explanations for a specific prediction under the form of (valid) compounds with high structural similarity and different predicted properties. Given a trained DGN, we train a reinforcement learning based generator to output counterfactual explanations. At each step, MEG feeds the current candidate counterfactual into the DGN, collects the prediction and uses it to reward the RL agent to guide the exploration. Furthermore, we restrict the action space of the agent in order to only keep actions that maintain the molecule in a valid state. We discuss the results showing how the model can convey non-ML experts with key insights into the learning model focus in the neighbourhood of a molecule.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/09/2020

Explaining Deep Graph Networks with Molecular Counterfactuals

We present a novel approach to tackle explainability of deep graph netwo...
research
01/29/2021

Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning

Counterfactual explanations, which deal with "why not?" scenarios, can p...
research
05/26/2020

Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)

Recently, a groundswell of research has identified the use of counterfac...
research
07/15/2023

Explainable AI with counterfactual paths

Explainable AI (XAI) is an increasingly important area of research in ma...
research
02/24/2022

Counterfactual Explanations for Predictive Business Process Monitoring

Predictive business process monitoring increasingly leverages sophistica...
research
03/08/2023

"How to make them stay?" – Diverse Counterfactual Explanations of Employee Attrition

Employee attrition is an important and complex problem that can directly...
research
12/18/2020

Semantics and explanation: why counterfactual explanations produce adversarial examples in deep neural networks

Recent papers in explainable AI have made a compelling case for counterf...

Please sign up or login with your details

Forgot password? Click here to reset