Decades before today's deep learning neural networks compiled imponderable layers of statistics into working machines, researchers were trying to figure out how one explains statistical findings to a human. IBM this week offered up the latest effort in that long quest to interpret, explain, and justify machine learning, a set of open-source programming resources it calls "AI 360 Explainability." It remains to be seen whether yet another tool will solve the conundrum of how people can understand what is going on when artificial intelligence makes a prediction based on data. The toolkit consists of eight different algorithms released in the course of 2018. The IBM tools are posted on Github as a Python library.

Art exhibition "Waterfall of Meaning" by Google PAIR displayed at the Barbican Curve Gallery. The rise of deep learning has been defined by a shift away from transparent and understandable human-written code towards sealed black boxes whose creators have little understanding of how or even why they yield the results they do. Concerns over bias, brittleness and flawed representations have led to growing interest in the area of "explainable AI" in which frameworks help interrogate a model's internal workings to shed light on precisely what it has learned about the world and help its developers nudge it towards a fairer and more faithful internal representation. As companies like Google roll out a growing stable of explainable AI tools like its What-If Tool, perhaps a more transparent and understandable deep learning future can help address the limitations that have slowed the field's deployment. Since the dawn of the computing revolution, the underlying programming that guided those mechanical thinking machines was provided by humans through transparent and visible instruction sets.

Decades of research in artificial intelligence (AI) have produced formidable technologies that are providing immense benefit to industry, government, and society. AI systems can now translate across multiple languages, identify objects in images and video, streamline manufacturing processes, and control cars. The deployment of AI systems has not only created a trillion-dollar industry that is projected to quadruple in three years, but has also exposed the need to make AI systems fair, explainable, trustworthy, and secure. Future AI systems will rightfully be expected to reason effectively about the world in which they (and people) operate, handling complex tasks and responsibilities effectively and ethically, engaging in meaningful communication, and improving their awareness through experience. Achieving the full potential of AI technologies poses research challenges that require a radical transformation of the AI research enterprise, facilitated by significant and sustained investment. These are the major recommendations of a recent community effort coordinated by the Computing Community Consortium and the Association for the Advancement of Artificial Intelligence to formulate a Roadmap for AI research and development over the next two decades.

With the increasing use of machine learning in practice and because of legal regulations like EU's GDPR, it becomes indispensable to be able to explain the prediction and behavior of machine learning models. An example of easy to understand explanations of AI models are counterfactual explanations. However, for many models it is still an open research problem how to efficiently compute counterfactual explanations. We investigate how to efficiently compute counterfactual explanations of learning vector quantization models. In particular, we propose different types of convex and non-convex programs depending on the used learning vector quantization model.

Current AI approaches have frequently been used to help personalize many aspects of medical experiences and tailor them to a specific individuals' needs. However, while such systems consider medically-relevant information, they ignore socially-relevant information about how this diagnosis should be communicated and discussed with the patient. The lack of this capability may lead to mis-communication, resulting in serious implications, such as patients opting out of the best treatment. Consider a case in which the same treatment is proposed to two different individuals. The manner in which this treatment is mediated to each should be different, depending on the individual patient's history, knowledge, and mental state. While it is clear that this communication should be conveyed via a human medical expert and not a software-based system, humans are not always capable of considering all of the relevant aspects and traversing all available information. We pose the challenge of creating Intelligent Agents (IAs) to assist medical service providers (MSPs) and consumers in establishing a more personalized human-to-human dialogue. Personalizing conversations will enable patients and MSPs to reach a solution that is best for their particular situation, such that a relation of trust can be built and commitment to the outcome of the interaction is assured. We propose a four-part conceptual framework for personalized social interactions, expand on which techniques are available within current AI research and discuss what has yet to be achieved.

Machine learning systems have become popular in fields such as marketing, financing, or data mining. While they are highly accurate, complex machine learning systems pose challenges for engineers and users. Their inherent complexity makes it impossible to easily judge their fairness and the correctness of statistically learned relations between variables and classes. Explainable AI aims to solve this challenge by modelling explanations alongside with the classifiers, potentially improving user trust and acceptance. However, users should not be fooled by persuasive, yet untruthful explanations. We therefore conduct a user study in which we investigate the effects of model accuracy and explanation fidelity, i.e. how truthfully the explanation represents the underlying model, on user trust. Our findings show that accuracy is more important for user trust than explainability. Adding an explanation for a classification result can potentially harm trust, e.g. when adding nonsensical explanations. We also found that users cannot be tricked by high-fidelity explanations into having trust for a bad classifier. Furthermore, we found a mismatch between observed (implicit) and self-reported (explicit) trust.

In the last years, abstract argumentation has met with great success in AI, since it has served to capture several non-monotonic logics for AI. Relations between argumentation framework (AF) semantics and logic programming ones are investigating more and more. In particular, great attention has been given to the well-known stable extensions of an AF, that are closely related to the answer sets of a logic program. However, if a framework admits a small incoherent part, no stable extension can be provided. To overcome this shortcoming, two semantics generalizing stable extensions have been studied, namely semi-stable and stage. In this paper, we show that another perspective is possible on incoherent AFs, called paracoherent extensions, as they have a counterpart in paracoherent answer set semantics. We compare this perspective with semi-stable and stage semantics, by showing that computational costs remain unchanged, and moreover an interesting symmetric behaviour is maintained. Under consideration for acceptance in TPLP.

Abstract Dialectical Frameworks (ADFs) are argumentation frameworks where each node is associated with an acceptance condition. This allows us to model different types of dependencies as supports and attacks. Previous studies provided a translation from Normal Logic Programs (NLPs) to ADFs and proved the stable models semantics for a normal logic program has an equivalent semantics to that of the corresponding ADF. However, these studies failed in identifying a semantics for ADFs equivalent to a three-valued semantics (as partial stable models and well-founded models) for NLPs. In this work, we focus on a fragment of ADFs, called Attacking Dialectical Frameworks (ADF$^+$s), and provide a translation from NLPs to ADF$^+$s robust enough to guarantee the equivalence between partial stable models, well-founded models, regular models, stable models semantics for NLPs and respectively complete models, grounded models, preferred models, stable models for ADFs. In addition, we define a new semantics for ADF$^+$s, called L-stable, and show it is equivalent to the L-stable semantics for NLPs. This paper is under consideration for acceptance in TPLP.

Post-hoc interpretability approaches have been proven to be powerful tools to generate explanations for the predictions made by a trained black-box model. However, they create the risk of having explanations that are a result of some artifacts learned by the model instead of actual knowledge from the data. This paper focuses on the case of counterfactual explanations and asks whether the generated instances can be justified, i.e. continuously connected to some ground-truth data. We evaluate the risk of generating unjustified counterfactual examples by investigating the local neighborhoods of instances whose predictions are to be explained and show that this risk is quite high for several datasets. Furthermore, we show that most state of the art approaches do not differentiate justified from unjustified counterfactual examples, leading to less useful explanations.

Value-based argumentation enhances a classical abstract argumentation graph - in which arguments are modelled as nodes connected by directed arrows called attacks - with labels on arguments, called values, and an ordering on values, called audience, to provide a more fine-grained justification of the attack relation. With more than one agent facing such an argumentation problem, agents may differ in their ranking of values. When needing to reach a collective view, such agents face a dilemma between two equally justifiable approaches: aggregating their views at the level of values, or aggregating their attack relations, remaining therefore at the level of the graphs. We explore the strenghts and limitations of both approaches, employing techniques from preference aggregation and graph aggregation, and propose a third possibility aggregating rankings extracted from given attack relations.