# explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning

## TL;DR

explAIner is a visual analytics system that enhances understanding, diagnosis, and refinement of machine learning models through an interactive explainable AI pipeline within TensorBoard.

## Contribution

It introduces a comprehensive framework combining multiple explainability and monitoring mechanisms, operationalized in a user-friendly visual analytics tool for ML model development.

## Key findings

- Users found the system improved understanding of models.
- The framework supports diagnosing model limitations effectively.
- User feedback highlighted areas for further system enhancement.

## Abstract

We propose a framework for interactive and explainable machine learning that enables users to (1) understand machine learning models; (2) diagnose model limitations using different explainable AI methods; as well as (3) refine and optimize the models. Our framework combines an iterative XAI pipeline with eight global monitoring and steering mechanisms, including quality monitoring, provenance tracking, model comparison, and trust building. To operationalize the framework, we present explAIner, a visual analytics system for interactive and explainable machine learning that instantiates all phases of the suggested pipeline within the commonly used TensorBoard environment. We performed a user-study with nine participants across different expertise levels to examine their perception of our workflow and to collect suggestions to fill the gap between our system and framework. The evaluation confirms that our tightly integrated system leads to an informed machine learning process while disclosing opportunities for further extensions.