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

Building interactive tools to support data analysis is hard because it is not always clear what to build and how to build it. To address this problem, we present Precision Interfaces, a semi-automatic system to generate task-specific data analytics interfaces. Precision Interface can turn a log of executed programs into an interface, by identifying micro-variations between the programs and mapping them to interface components. This paper focuses on SQL query logs, but we can generalize the approach to other languages. Our system operates in two steps: it first build an interaction graph, which describes how the queries can be transformed into each other. Then, it finds a set of UI components that covers a maximal number of transformations. To restrict the domain of changes to be detected, our system uses a domain-specific language, PILang. We give a full description of Precision Interface's components, showcase an early prototype on real program logs and discuss future research opportunities.

Precision Interfaces

Live video-streaming platforms such as Twitch enable top content creators to reap significant profits and influence. To that effect, various behavioral norms are recommended to new entrants and those seeking to increase their popularity and success. Chiefly among them are to simply put in the effort and promote on social media outlets such as Twitter, Instagram, and the like. But does following these behaviors indeed have a relationship with eventual popularity? 
In this paper, we collect a corpus of Twitch streamer popularity measures --- spanning social and financial measures --- and their behavior data on Twitch and third party platform. We also compile a set of community-defined behavioral norms. We then perform temporal analysis to identify the increased predictive value that a streamer's future behavior contributes to predicting future popularity. At the population level, we find that behavioral information improves the prediction of relative growth that exceeds the median streamer. At the individual level, we find that although it is difficult to quickly become successful in absolute terms, streamers that put in considerable effort are more successful than the rest, and that creating social media accounts to promote oneself is effective irrespective of when the accounts are created. Ultimately, we find that studying the popularity and success of content creators in the long term is a promising and rich research area.

PopFactor: Live-Streamer Behavior and Popularity

— A hallmark of visual analytics is its ability to support users in translating broad, open-ended analytic questions (e.g., “is our company succeeding?”) into veriﬁable hypotheses that can be tested from the available data (e.g., “our total revenue increased this past quarter”). However, the process of converting open-ended analytic questions into testable hypotheses is complex and often ill-deﬁned. Beyond high-level descriptions, the visual analytics literature lacks a formalization that can be operationalized for analysis and automation. In this paper, we propose a novel grammar to express hypothesis-based analytic questions for visual analysis. Drawing from prior work in science and education, our grammar deﬁnes a formal way to express sets of veriﬁable hypotheses as a “hypothesis space”. Our proposed use of hypothesis spaces contributes a new lens to unify concepts of user goals, the capabilities of a dataset, visual analysis, and testable hypotheses. As a result, we can reformulate abstract classes of visual analysis goals, such as analytic and data-related tasks, in a way that is suitable for analysis and automation. We demonstrate use cases of our grammar in real-world analytic applications including VAST challenges, Kaggle competitions, and pre-existing task taxonomies. Finally, we provide design opportunities in which our grammar can be operationalized to articulate analysis tasks, evaluate visualization systems, and support hypothesis-based reasoning in visual analytic tools.

A Grammar for Hypothesis-Driven Visual Analysis

We demonstrate PVD, a system that visualization designers can use to co-design the interface and system architecture of scalable and expressive visualization.

https://dl.acm.org/doi/pdf/10.1145/3318464.3384711

Physical Visualization Design

AutoML services provide a way for non-expert users to benefit from high-quality ML models without worrying about model design and deployment, in exchange for a charge per hour ($21.252 for VertexAI). However, existing AutoML services are model-centric, in that they are limited to extracting features and searching for models from initial training data-they are only as effective as the initial training data quality. With the increasing volume of tabular data available, there is a huge opportunity for data augmentation. For instance, vertical augmentation adds predictive features, while horizontal augmentation adds examples. This augmented training data yields potentially much better AutoML models at a lower cost. However, existing systems either forgo the augmentation opportunities that provide poor models, or apply expensive augmentation searching techniques that drain users' budgets. Kitana is a data-centric AutoML system that also searches for new tabular datasets that can augment the tabular training data with new features and/or examples. Kitana manages a corpus of datasets, exposes an AutoML interface to users and searches for augmentation with datasets in the corpus to improve AutoML performance. To accelerate search, Kitana applies aggressive pre-computation to train a factorized proxy model and evaluate each candidate augmentation within 0.1s. Kitana also uses a cost model to limit the time spent on augmentation search, supports expressive data access controls, and performs request caching to benefit from past similar requests. Using a corpus of 518 open-source datasets, Kitana produces higher quality models than existing AutoML systems in orders of magnitude less time. Across different user requests, Kitana increases the model R2 from 0.16 to 0.66 while reducing the cost by>100x compared to the naive factorized learning and SOTA data augmentation search.

Eugene Wu

Papers

Precision Interfaces

PopFactor: Live-Streamer Behavior and Popularity

A Grammar for Hypothesis-Driven Visual Analysis

Physical Visualization Design

Kitana: Efficient Data Augmentation Search for AutoML