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

In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.

https://dl.acm.org/doi/pdf/10.1145/3236009

A Survey of Methods for Explaining Black Box Models

Recent years have witnessed a proliferation of large-scale knowledge bases, including Wikipedia, Freebase, YAGO, Microsoft's Satori, and Google's Knowledge Graph. To increase the scale even further, we need to explore automatic methods for constructing knowledge bases. Previous approaches have primarily focused on text-based extraction, which can be very noisy. Here we introduce Knowledge Vault, a Web-scale probabilistic knowledge base that combines extractions from Web content (obtained via analysis of text, tabular data, page structure, and human annotations) with prior knowledge derived from existing knowledge repositories. We employ supervised machine learning methods for fusing these distinct information sources. The Knowledge Vault is substantially bigger than any previously published structured knowledge repository, and features a probabilistic inference system that computes calibrated probabilities of fact correctness. We report the results of multiple studies that explore the relative utility of the different information sources and extraction methods.

/pdf/knowledge-vault-a-web-scale-approach-to-probabilistic-23hsir1ibs.pdf

Knowledge vault: a web-scale approach to probabilistic knowledge fusion

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.

At Brown University, there is excitement of having access to the Brown Corpus, containing one million English words. Since then, we have seen several notable corpora that are about 100 times larger, and in 2006, Google released a trillion-word corpus with frequency counts for all sequences up to five words long. In some ways this corpus is a step backwards from the Brown Corpus: it's taken from unfiltered Web pages and thus contains incomplete sentences, spelling errors, grammatical errors, and all sorts of other errors. It's not annotated with carefully hand-corrected part-of-speech tags. But the fact that it's a million times larger than the Brown Corpus outweighs these drawbacks. A trillion-word corpus - along with other Web-derived corpora of millions, billions, or trillions of links, videos, images, tables, and user interactions - captures even very rare aspects of human behavior. So, this corpus could serve as the basis of a complete model for certain tasks - if only we knew how to extract the model from the data.

http://rakaposhi.eas.asu.edu/cse571/unreasonable.pdf

The Unreasonable Effectiveness of Data

Data science instructors often find it hard to explain to students how a piece of code written in Python, R, or SQL executes in order to transform tabular data. They currently resort to hand-drawing diagrams or making presentation slides to illustrate the semantics of operations such as filtering, sorting, reshaping, pivoting, grouping, and joining. These diagrams are time-consuming to create and do not synchronize with real code or data that students are learning about. In this paper we show that a step-by-step visual representation of tabular data transforms can help instructors to explain these operations. To do so, we created a table visualization library that illustrates the row-, column-, and cell-wise relationships between an operation's input and output tables. On top of this library we built a trio of free web-based visualization tools - Pandas Tutor for Python, Tidy Data Tutor for R tidyverse, and SQL Tutor - that run users' code and automatically produce diagrams of how Python/R/SQL transforms data tables step-by-step from input to output. Since launching in Dec 2021, over 61,000 people from over 160 countries have visited our website to try out these tools.

https://dl.acm.org/doi/pdf/10.1145/3596673.3596972

Teaching Data Science by Visualizing Data Table Transformations: Pandas Tutor for Python, Tidy Data Tutor for R, and SQL Tutor

Any system at play in a data-driven project has a fundamental requirement: the ability to load data. The de-facto standard format to distribute and consume raw data is csv. Yet, the plain text and flexible nature of this format make such files often difficult to parse and correctly load their content, requiring cumbersome data preparation steps. We propose a benchmark to assess the robustness of systems in loading data from non-standard csv formats and with structural inconsistencies. First, we formalize a model to describe the issues that affect real-world files and use it to derive a systematic "pollution" process to generate dialects for any given grammar. Our benchmark leverages the pollution framework for the csv format. To guide pollution, we have surveyed thousands of real-world, publicly available csv files, recording the problems we encountered. We demonstrate the applicability of our benchmark by testing and scoring 16 different systems: popular csv parsing frameworks, relational database tools, spreadsheet systems, and a data visualization tool.

Pollock: A Data Loading Benchmark

Animated and interactive data visualizations dynamically change the data rendered in a visualization (e.g., bar chart). As the data changes, the y-axis may need to be rescaled as the domain of the data changes. Each axis rescaling potentially improves the readability of the current chart, but may also disorient the user. In contrast to static visualizations, where there is considerable literature to help choose the appropriate y-axis scale, there is a lack of guidance about how and when rescaling should be used in dynamic visualizations. Existing visualization systems and libraries adapt a fixed global y-axis, or rescale every time the data changes. Yet, professional visualizations, such as in data journalism, do not adopt either strategy. They instead carefully and manually choose when to rescale based on the analysis task and data. To this end, we conduct a series of Mechanical Turk experiments to study the potential of dynamic axis rescaling and the factors that affect its effectiveness. We find that the appropriate rescaling policy is both task- and data-dependent, and we do not find one clear policy choice for all situations.

Automatic Y-axis Rescaling in Dynamic Visualizations

Recent query explanation systems help users understand anomalies in aggregation results by proposing predicates that describe input records that, if deleted, would resolve the anomalies. However, it can be difficult for users to understand how a predicate was chosen, and these approaches are limited to errors that can be resolved through deletion. In contrast, data errors may be due to group-wise errors, such as missing records or systematic value errors. This paper presents Reptile, an explanation system for hierarchical data. Given an anomalous aggregate query result, Reptile recommends the next drill-down attribute,and ranks the drill-down groups based on the extent repairing the group's statistics to its expected values resolves the anomaly. Reptile efficiently trains a multi-level model that leverages the data's hierarchy to estimate the expected values, and uses a factorised representation of the feature matrix to remove redundancies due to the data's hierarchical structure. We further extend model training to support factorised data, and develop a suite of optimizations that leverage the data's hierarchical structure. Reptile reduces end-to-end runtimes by more than 6 times compared to a Matlab-based implementation, correctly identifies 21/30 data errors in John Hopkin's COVID-19 data, and correctly resolves 20/22 complaints in a user study using data and researchers from Columbia University's Financial Instruments Sector Team.

Reptile: Aggregation-level Explanations for Hierarchical Data

Modern social media relies on high quality user generated writing such as reviews, explanations, and answers. In contrast to standard validation to provide feedback for structured inputs (e.g., dates, email addresses), it is difficult to provide timely, high quality, customized feedback for free-form text input. While existing solutions based on crowdsourced feedback (e.g., up-votes and comments) can eventually produce high quality feedback, they suffer from high latency and costs, whereas fully automated approaches are limited to syntactic feedback that does not address text content. We introduce Dialectic, an end-to-end extensible system that simplifies the process of creating, customizing, and deploying content-specific feedback for free-text inputs. Our main observation is that many services already have a corpus of crowdsourced feedback that can be used to bootstrap a feedback system. Dialectic initializes with a corpus of annotated free-form text, automatically segments input text, and helps developers rapidly add domain-specific document quality features as well as content-specific feedback generation functions to provide targeted feedback to user inputs. Our user study shows that Dialectic can be used to create a feedback interface that produces an average of 14.4\% quality improvement of product review text, over 3x better than a state-of-the-art feedback system.

Eugene Wu

Papers

Teaching Data Science by Visualizing Data Table Transformations: Pandas Tutor for Python, Tidy Data Tutor for R, and SQL Tutor

Pollock: A Data Loading Benchmark

Automatic Y-axis Rescaling in Dynamic Visualizations

Reptile: Aggregation-level Explanations for Hierarchical Data

Dialectic: Enhancing Text Input Fields with Automatic Feedback to Improve Social Content Writing Quality.