We are excited to bring Transform 2022 back in-person July 19 and virtually July 20 - 28. Join AI and data leaders for insightful talks and exciting networking opportunities. Artificial intelligence (AI) is highly effective at parsing extreme volumes of data and making decisions based on information that is beyond the limits of human comprehension. But it suffers from one serious flaw: it cannot explain how it arrives at the conclusions it presents, at least, not in a way that most people can understand. This "black box" characteristic is starting to throw some serious kinks in the applications that AI is empowering, particularly in medical, financial and other critical fields, where the "why" of any particular action is often more important than the "what." This is leading to a new field of study called explainable AI (XAI), which seeks to infuse AI algorithms with enough transparency so users outside the realm of data scientists and programmers can double-check their AI's logic to make sure it is operating within the bounds of acceptable reasoning, bias and other factors.

Counterfactual explanations (CFEs) highlight what changes to a model's input would have changed its prediction in a particular way. CFEs have gained considerable traction as a psychologically grounded solution for explainable artificial intelligence (XAI). Recent innovations introduce the notion of computational plausibility for automatically generated CFEs, enhancing their robustness by exclusively creating plausible explanations. However, practical benefits of such a constraint on user experience and behavior is yet unclear. In this study, we evaluate objective and subjective usability of computationally plausible CFEs in an iterative learning design targeting novice users. We rely on a novel, game-like experimental design, revolving around an abstract scenario. Our results show that novice users actually benefit less from receiving computationally plausible rather than closest CFEs that produce minimal changes leading to the desired outcome. Responses in a post-game survey reveal no differences in terms of subjective user experience between both groups. Following the view of psychological plausibility as comparative similarity, this may be explained by the fact that users in the closest condition experience their CFEs as more psychologically plausible than the computationally plausible counterpart. In sum, our work highlights a little-considered divergence of definitions of computational plausibility and psychological plausibility, critically confirming the need to incorporate human behavior, preferences and mental models already at the design stages of XAI approaches. In the interest of reproducible research, all source code, acquired user data, and evaluation scripts of the current study are available: https://github.com/ukuhl/PlausibleAlienZoo

To foster usefulness and accountability of machine learning (ML), it is essential to explain a model's decisions in addition to evaluating its performance. Accordingly, the field of explainable artificial intelligence (XAI) has resurfaced as a topic of active research, offering approaches to address the "how" and "why" of automated decision-making. Within this domain, counterfactual explanations (CFEs) have gained considerable traction as a psychologically grounded approach to generate post-hoc explanations. To do so, CFEs highlight what changes to a model's input would have changed its prediction in a particular way. However, despite the introduction of numerous CFE approaches, their usability has yet to be thoroughly validated at the human level. Thus, to advance the field of XAI, we introduce the Alien Zoo, an engaging, web-based and game-inspired experimental framework. The Alien Zoo provides the means to evaluate usability of CFEs for gaining new knowledge from an automated system, targeting novice users in a domain-general context. As a proof of concept, we demonstrate the practical efficacy and feasibility of this approach in a user study. Our results suggest that users benefit from receiving CFEs compared to no explanation, both in terms of objective performance in the proposed iterative learning task, and subjective usability. With this work, we aim to equip research groups and practitioners with the means to easily run controlled and well-powered user studies to complement their otherwise often more technology-oriented work. Thus, in the interest of reproducible research, we provide the entire code, together with the underlying models and user data.

Less than a year ago, Anthropic was founded by former OpenAI VP of research Dario Amodei, intending to perform research in the public interest on making AI more reliable and explainable. Its $124 million in funding was surprising then, but nothing could have prepared us for the company raising $580 million less than a year later. "With this fundraise, we're going to explore the predictable scaling properties of machine learning systems, while closely examining the unpredictable ways in which capabilities and safety issues can emerge at-scale," said Amodei in the announcement. His sister Daniela, with whom he co-founded the public benefit corporation, said that having built out the company, "We're focusing on ensuring Anthropic has the culture and governance to continue to responsibly explore and develop safe AI systems as we scale." Because that's the problem category Anthropic was formed to examine: how to better understand the AI models increasingly in use in every industry as they grow beyond our ability to explain their logic and outcomes.

Just like a coin, explainability in AI has two faces -- one it shows to the developers (who actually build the models) and the other to the users (the end customers). The former face (IE i.e. intrinsic explainability) is a technical indicator to the builder that explains the working of the model. Whereas the latter (EE i.e. extrinsic explainability) is proof to the customers about the model's predictions. While IE is required for any reasonable model improvement, we need EE for factual confirmation. A simple layman who ends up using the model's prediction needs to know why is the model suggesting something.

Artificial intelligence (AI) systems power the world we live in. Deep neural networks (DNNs) are able to solve tasks in an ever-expanding landscape of scenarios, but our eagerness to apply these powerful models leads us to focus on their performance and deprioritises our ability to understand them. Current research in the field of explainable AI tries to bridge this gap by developing various perturbation or gradient-based explanation techniques. For images, these techniques fail to fully capture and convey the semantic information needed to elucidate why the model makes the predictions it does. In this work, we develop a new form of explanation that is radically different in nature from current explanation methods, such as Grad-CAM.

The energy transition introduces more volatile energy sources into the power grids. In this context, power transfer between different synchronous areas through High Voltage Direct Current (HVDC) links becomes increasingly important. Such links can balance volatile generation by enabling long-distance transport or by leveraging their fast control behavior. Here, we investigate the interaction of power imbalances - represented through the power grid frequency - and power flows on HVDC links between synchronous areas in Europe. We use explainable machine learning to identify key dependencies and disentangle the interaction of critical features. Our results show that market-based HVDC flows introduce deterministic frequency deviations, which however can be mitigated through strict ramping limits. Moreover, varying HVDC operation modes strongly affect the interaction with the grid. In particular, we show that load-frequency control via HVDC links can both have control-like or disturbance-like impacts on frequency stability.

Counterfactual explanations are increasingly used to address interpretability, recourse, and bias in AI decisions. However, we do not know how well counterfactual explanations help users to understand a systems decisions, since no large scale user studies have compared their efficacy to other sorts of explanations such as causal explanations (which have a longer track record of use in rule based and decision tree models). It is also unknown whether counterfactual explanations are equally effective for categorical as for continuous features, although current methods assume they do. Hence, in a controlled user study with 127 volunteer participants, we tested the effects of counterfactual and causal explanations on the objective accuracy of users predictions of the decisions made by a simple AI system, and participants subjective judgments of satisfaction and trust in the explanations. We discovered a dissociation between objective and subjective measures: counterfactual explanations elicit higher accuracy of predictions than no-explanation control descriptions but no higher accuracy than causal explanations, yet counterfactual explanations elicit greater satisfaction and trust than causal explanations. We also found that users understand explanations referring to categorical features more readily than those referring to continuous features. We discuss the implications of these findings for current and future counterfactual methods in XAI.

Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. However, the major shortcoming associated with these methods is their inability to provide explanations beyond the local or instance-level. While some works touch upon the notion of a global explanation, typically suggesting to aggregate masses of local explanations in the hope of ascertaining global properties, few provide frameworks that are either reliable or computationally tractable. Meanwhile, practitioners are requesting more efficient and interactive explainability tools. We take this opportunity to investigate existing global methods, with a focus on implementing and improving Actionable Recourse Summaries (AReS), the only known global counterfactual explanation framework for recourse.

DARPA, In-Q-Tel, US National Laboratories (examples: Argonne, Oak Ridge) are famous government funding agencies for deep tech on the forward boundaries, the near impossible, that have globally transformative solutions. The Internet is a prime example where more than 70% of the 7.8 billion population are online in 2022, closing in on 7 hours daily mobile usage, and global wealth of $500 Trillion is powered by the Internet. There is convergence between the early bets led by government funding agencies and the largest corporations and their investments. An example is from 2015, where I was invited to help the top 100 CEOs, representing nearly $100 Trillion in assets under management, to look ten years into the future for their investments. The resulting working groups, and private summits resulted in the member companies investing in all the areas identified: quantum computing, block chain, cybersecurity, big data, privacy and data, AI/ML, future in fintech, financial inclusion, ...