Survey of Explainable Machine Learning with Visual and Granular Methods Beyond Quasi-Explanations

Abstract

This chapter surveys and analyses visual methods of explainabilityExplainability of Machine Learning (ML)Machine learning approaches with focus on moving from quasi-explanations that dominate in ML to actual domain-specific explanation supported by granular visuals. The importance of visual and granular methods to increase the interpretabilityInterpretability and validity of the ML model has grown in recent years. Visuals have an appeal to human perception, which other methods do not. ML interpretation is fundamentally a human activity, not a machine activity. Thus, visual methods are more readily interpretable. Visual granularityGranularity is a natural way for efficient ML explanation. Understanding complex causal reasoning can be beyond human abilities without “downgrading” it to human perceptual and cognitive limits. The visual exploration of multidimensional data at different levels of granularityGranularity for knowledge discovery is a long-standing research focus. While multiple efficient methods for visual representation of high-dimensional data exist, the loss of interpretable information, occlusion, and clutter continue to be a challenge, which lead to quasi-explanations. This chapter starts with the motivation and the definitions of different forms of explainabilityExplainability and how these concepts and information granularityGranularity can integrate in ML. The chapter focuses on a clear distinction between quasi-explanations and actual domain specific explanations, as well as between potentially explainable and an actually explained ML model that are critically important for the further progress of the ML explainabilityExplainability domain. We discuss foundations of interpretabilityInterpretability, overview visual interpretabilityInterpretability and present several types of methods to visualize the ML models. Next, we present methods of visual discovery of ML models, with the focus on interpretable models, based on the recently introduced concept of General Line CoordinatesGeneral line coordinates (GLC). This family of methods take the critical step of creating visual explanations that are not merely quasi-explanations but are also domain specific visual explanations while these methods themselves are domain-agnostic. The chapter includes results on theoretical limits to preserve n-D distances in lower dimensions, based on the Johnson-Lindenstrauss lemma, point-to-point and point-to-graph GLC approaches, and real-world case studies. The chapter also covers traditional visual methods for understanding multiple ML models, which include deep learningDeep learning and time series models. We illustrate that many of these methods are quasi-explanations and need further enhancement to become actual domain specific explanations. The chapter concludes with outlining open problems and current research frontiers.