A Learning-Based Method for Automatic Operator Selection in the Fanoos XAI System

TL;DR

This paper introduces a learning-based extension to the Fanoos XAI system that enables automatic operator selection for generating descriptions at varying levels of abstraction, improving adaptability and efficiency.

Contribution

It presents a method for Fanoos to learn optimal operator selection using experience, balancing exploration and exploitation, and introduces a simulated user for bootstrap learning.

Findings

Fanoos can now learn to select operators effectively based on past experience.

The simulated user helps bootstrap the learning process for better initial performance.

The approach improves the system's ability to generate appropriate descriptions at different abstraction levels.

Abstract

We describe an extension of the Fanoos XAI system [Bayani et al 2022] which enables the system to learn the appropriate action to take in order to satisfy a user's request for description to be made more or less abstract. Specifically, descriptions of systems under analysis are stored in states, and in order to make a description more or less abstract, Fanoos selects an operator from a large library to apply to the state and generate a new description. Prior work on Fanoos predominately used hand-written methods for operator-selection; this current work allows Fanoos to leverage experience to learn the best operator to apply in a particular situation, balancing exploration and exploitation, leveraging expert insights when available, and utilizing similarity between the current state and past states. Additionally, in order to bootstrap the learning process (i.e., like in curriculum learning), we describe a simulated user which we implemented; this simulation allows Fanoos to gain general insights that enable reasonable courses of action, insights which later can be refined by experience with real users, as opposed to interacting with humans completely from scratch. Code implementing the methods described in the paper can be found at https://github/DBay-ani/Operator_Selection_Learning_Extensions_For_Fanoos.