Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

In the last years, Artificial Intelligence (AI) has achieved a notable momentum that may deliver the best of expectations over many application sectors across the field. For this to occur, the entire community stands in front of the barrier of explainability, an inherent problem of AI techniques brought by sub-symbolism (e.g. ensembles or Deep Neural Networks) that were not present in the last hype of AI. Paradigms underlying this problem fall within the so-called eXplainable AI (XAI) field, which is acknowledged as a crucial feature for the practical deployment of AI models. This overview examines the existing literature in the field of XAI, including a prospect toward what is yet to be reached. We summarize previous efforts to define explainability in Machine Learning, establishing a novel definition that covers prior conceptual propositions with a major focus on the audience for which explainability is sought. We then propose and discuss about a taxonomy of recent contributions related to the explainability of different Machine Learning models, including those aimed at Deep Learning methods for which a second taxonomy is built. This literature analysis serves as the background for a series of challenges faced by XAI, such as the crossroads between data fusion and explainability. Our prospects lead toward the concept of Responsible Artificial Intelligence, namely, a methodology for the large-scale implementation of AI methods in real organizations with fairness, model explainability and accountability at its core. Our ultimate goal is to provide newcomers to XAI with a reference material in order to stimulate future research advances, but also to encourage experts and professionals from other disciplines to embrace the benefits of AI in their activity sectors, without any prior bias for its lack of interpretability.

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI.

Machine learning systems are becoming increasingly ubiquitous. These systems’s adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability of decisions mandatory, increasing the demand for the ability to question, understand, and trust machine learning systems, for which interpretability is indispensable. The research community has recognized this interpretability problem and focused on developing both interpretable models and explanation methods over the past few years. However, the emergence of these methods shows there is no consensus on how to assess the explanation quality. Which are the most suitable metrics to assess the quality of an explanation? The aim of this article is to provide a review of the current state of the research field on machine learning interpretability while focusing on the societal impact and on the developed methods and metrics. Furthermore, a complete literature review is presented in order to identify future directions of work on this field.

Machine Learning Interpretability: A Survey on Methods and Metrics

A number of algorithms in the field of artificial intelligence offer poorly interpretable decisions. To disclose the reasoning behind such algorithms, their output can be explained by means of so-called evidence-based (or factual) explanations. Alternatively, contrastive and counterfactual explanations justify why the output of the algorithms is not any different and how it could be changed, respectively. It is of crucial importance to bridge the gap between theoretical approaches to contrastive and counterfactual explanation and the corresponding computational frameworks. In this work we conduct a systematic literature review which provides readers with a thorough and reproducible analysis of the interdisciplinary research field under study. We first examine theoretical foundations of contrastive and counterfactual accounts of explanation. Then, we report the state-of-the-art computational frameworks for contrastive and counterfactual explanation generation. In addition, we analyze how grounded such frameworks are on the insights from the inspected theoretical approaches. As a result, we highlight a variety of properties of the approaches under study and reveal a number of shortcomings thereof. Moreover, we define a taxonomy regarding both theoretical and practical approaches to contrastive and counterfactual explanation.

/pdf/a-survey-of-contrastive-and-counterfactual-explanation-47ollkua13.pdf

A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence

Visual Question Answering (VQA) models tend to rely on the language bias and thus fail to learn the reasoning from visual knowledge, which is however the original intention of VQA. In this paper, we propose a novel cause-effect look at the language bias, where the bias is formulated as the direct effect of question on answer from the view of causal inference. The effect can be captured by counterfactual VQA, where the image had not existed in an imagined scenario. Our proposed cause-effect look 1) is general to any baseline VQA architecture, 2) achieves significant improvement on the language-bias sensitive VQA-CP dataset, and 3) fills the theoretical gap in recent language prior based works.

Counterfactual VQA: A Cause-Effect Look at Language Bias

In this paper, we specifically examine the training of a multi-label classifier from data with incompletely assigned labels. This problem is fundamentally important in many multi-label applications because it is almost impossible for human annotators to assign a complete set of labels, although their judgments are reliable. In other words, a multilabel dataset usually has properties by which (1) assigned labels are definitely positive and (2) some labels are absent but are still considered positive. Such a setting has been studied as a positive and unlabeled (PU) classification problem in a binary setting. We treat incomplete label assignment problems as a multi-label PU ranking, which is an extension of classical binary PU problems to the wellstudied rank-based multi-label classification. We derive the conditions that should be satisfied to cancel the negative effects of label incompleteness. Our experimentally obtained results demonstrate the effectiveness of these conditions.

/pdf/multi-label-ranking-from-positive-and-unlabeled-data-l27hqvnklo.pdf

Multi-label Ranking from Positive and Unlabeled Data

This paper addresses the generation of explanations with visual examples. Given an input sample, we build a system that not only classifies it to a specific category, but also outputs linguistic explanations and a set of visual examples that render the decision interpretable. Focusing especially on the complementarity of the multimodal information, i.e., linguistic and visual examples, we attempt to achieve it by maximizing the interaction information, which provides a natural definition of complementarity from an information theoretical viewpoint. We propose a novel framework to generate complemental explanations, on which the joint distribution of the variables to explain, and those to be explained is parameterized by three different neural networks: predictor, linguistic explainer, and example selector. Explanation models are trained collaboratively to maximize the interaction information to ensure the generated explanation are complemental to each other for the target. The results of experiments conducted on several datasets demonstrate the effectiveness of the proposed method.

/pdf/learning-to-explain-with-complemental-examples-21ardq7iuu.pdf

Learning to Explain With Complemental Examples

We present a novel dataset and a novel algorithm for recognizing activities of daily living (ADL) from a first-person wearable camera. Handled objects are crucially important for egocentric ADL recognition. For specific examination of objects related to users' actions separately from other objects in an environment, many previous works have addressed the detection of handled objects in images captured from head-mounted and chest-mounted cameras. Nevertheless, detecting handled objects is not always easy because they tend to appear small in images. They can be occluded by a user's body. As described herein, we mount a camera on a user's wrist. A wrist-mounted camera can capture handled objects at a large scale, and thus it enables us to skip the object detection process. To compare a wrist-mounted camera and a head-mounted camera, we also developed a novel and publicly available dataset 1 that includes videos and annotations of daily activities captured simultaneously by both cameras. Additionally, we propose a discriminative video representation that retains spatial and temporal information after encoding the frame descriptors extracted by convolutional neural networks (CNN).

/pdf/recognizing-activities-of-daily-living-with-a-wrist-mounted-13n41fnlzr.pdf

Recognizing Activities of Daily Living with a Wrist-Mounted Camera

This study addresses generating counterfactual explanations with multimodal information. Our goal is not only to classify a video into a specific category, but also to provide explanations on why it is not categorized to a specific class with combinations of visual-linguistic information. Requirements that the expected output should satisfy are referred to as counterfactuality in this paper: (1) Compatibility of visual-linguistic explanations, and (2) Positiveness/negativeness for the specific positive/negative class. Exploiting a spatio-temporal region (tube) and an attribute as visual and linguistic explanations respectively, the explanation model is trained to predict the counterfactuality for possible combinations of multimodal information in a post-hoc manner. The optimization problem, which appears during training/inference, can be efficiently solved by inserting a novel neural network layer, namely the maximum subpath layer. We demonstrated the effectiveness of this method by comparison with a baseline of the action recognition datasets extended for this task. Moreover, we provide information-theoretical insight into the proposed method.

/pdf/multimodal-explanations-by-predicting-counterfactuality-in-2hbp7062i2.pdf

Multimodal Explanations by Predicting Counterfactuality in Videos

This paper introduces a novel variant of video summarization, namely building a summary that depends on the particular aspect of a video the viewer focuses on. We refer to this as viewpoint. To infer what the desired viewpoint may be, we assume that several other videos are available, especially groups of videos, e.g., as folders on a person's phone or laptop. The semantic similarity between videos in a group vs. the dissimilarity between groups is used to produce viewpoint-specific summaries. For considering similarity as well as avoiding redundancy, output summary should be (A) diverse, (B) representative of videos in the same group, and (C) discriminative against videos in the different groups. To satisfy these requirements (A)-(C) simultaneously, we proposed a novel video summarization method from multiple groups of videos. Inspired by Fisher's discriminant criteria, it selects summary by optimizing the combination of three terms (a) inner-summary, (b) inner-group, and (c) between-group variances defined on the feature representation of summary, which can simply represent (A)-(C). Moreover, we developed a novel dataset to investigate how well the generated summary reflects the underlying viewpoint. Quantitative and qualitative experiments conducted on the dataset demonstrate the effectiveness of proposed method.

/pdf/viewpoint-aware-video-summarization-3en44mw91u.pdf

Atsushi Kanehira

Papers

Multi-label Ranking from Positive and Unlabeled Data

Learning to Explain With Complemental Examples

Recognizing Activities of Daily Living with a Wrist-Mounted Camera

Multimodal Explanations by Predicting Counterfactuality in Videos

Viewpoint-Aware Video Summarization