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

Abstract

This chapter surveys and analyses visual methods of explainability of Machine Learning (ML) 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 interpretability 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 granularity 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 granularity 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 quasiexplanations. This chapter starts with the motivation and the definitions of different forms of explainability and how these concepts and information granularity 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 explainability domain. We discuss foundations of interpretability, overview visual interpretability 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 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, pointto-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 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.

Applications of Learning Analytics in High Schools: A Systematic Literature Review

“… 4. Explainable artificial intelligence : Although this literature review highlighted the importance of using white-box machine learning methods, recent literature proposes the combination of deep learning with explainable artificial intelligence techniques in the analysis of educational data ( Kovalerchuk et al, 2021 ). Specifically in learning analytics, explainable artificial intelligence is still at an initial adoption step, but researchers have already reported positive results ( Verbert et al, 2020 ; Ochoa and Wise, 2021 ).…”

Visual Analytics for Human-Centered Machine Learning

“…Some ML researchers argue that the current XAI approaches fail to provide satisfactory explanations that can be well understood by humans, i.e., linked to their mental models. The term "explainability" is contrasted with "explanation" [12] and "causability" [9]. According to Kovalerchuk et al [12], a model is truly explained if a domain expert accepts it based on both empirical evidence of satisfactory accuracy and the domain knowledge/theory/reasoning, which is beyond a given dataset.…”

“…The term "explainability" is contrasted with "explanation" [12] and "causability" [9]. According to Kovalerchuk et al [12], a model is truly explained if a domain expert accepts it based on both empirical evidence of satisfactory accuracy and the domain knowledge/theory/reasoning, which is beyond a given dataset. Instead, XAI methods generate "quasi-explanations", which refer to components and properties of data and specifics of the modelling algorithm but do not explain models in terms of domain knowledge and concepts that humans use in their reasoning.…”

“…However, there is a tendency to admit that model "explainability" does not necessarily mean that the model is indeed properly explained to humans and understood by them [9,12]. In this paper, we discuss the deficiencies of the common approaches to explaining ML models, mention current efforts towards overcoming these deficiencies, argue why Visual Analytics (VA) [11] should be involved in such efforts, and consider its possible role in helping humans to understand models.…”

Lossless Visual Knowledge Discovery in High Dimensional Data with Elliptic Paired Coordinates

“…An alternative methodology is mapping n-D points to 2-D graphs that preserves all n-D information [1,2,5,13]. Elliptic Paired Coordinates belong to the later.…”