Explainable AI Seminars @ Imperial

CLArg Group, Centre for eXplainable Artificial Intelligence, Imperial College London

XAI has witnessed unprecedented growth in both academia and industry in recent years (alongside AI itself), given its crucial role in supporting human-AI partnerships. XAI allows to deploy opaque data-driven AI methods safely in a variety of settings, such as finance, healthcare and law. XAI is positioned at the intersection of AI, human-computer interaction, the social sciences (in particular psychology) and applications.
Overall, XAI is increasingly part of all AI policies on ethics, trustworthiness and safety of AI. This seminar series focuses on all aspects of XAI, ranging from methods to applications.

Get invites in your inbox - Sign up here

Next Seminar

Nils Breuer - "CAGE: Causality-Aware Shapley Value for Global Explanations"

21^st November, 16:00 BST, on Microsoft Teams (join online).

Abstract

As Artificial Intelligence (AI) is having more influence on our everyday lives, it becomes important that AI-based decisions are transparent and explainable. As a consequence, the field of eXplainable AI (or XAI) has become popular in recent years. One way to explain AI models is to elucidate the predictive importance of the input features for the AI model in general, also referred to as global explanations. Inspired by cooperative game theory, Shapley values offer a convenient way for quantifying the feature importance as explanations. However many methods based on Shapley values are built on the assumption of feature independence and often overlook causal relations of the features which could impact their importance for the ML model. Inspired by studies of explanations at the local level, we propose CAGE (Causally-Aware Shapley Values for Global Explanations). In particular, we introduce a novel sampling procedure for out-coalition features that respects the causal relations of the input features. We derive a practical approach that incorporates causal knowledge into global explanation and offers the possibility to interpret the predictive feature importance considering their causal relation. We evaluate our method on synthetic data and real-world data. The explanations from our approach suggest that they are not only more intuitive but also more faithful compared to previous global explanation methods.

Bio

After a bachelor's degree in cognitive science at the University of Tübingen and a master's degree in artificial intelligence at the Vrije Universiteit Amsterdam, I am now a PhD student at the Technical University Berlin supervised by Prof. Dr. Dr. Sahin Albayrak. My research focus lies between the topics of causality and interpretable AI. I investigate how methods of causality and interpretability are linked and how they can benefit from each other. In addition, I am investigating in a government-funded research project called goKI (German abbreviation for artificial intelligence for the common good) how common good-oriented AI applications can be made transparent and explainable for a diverse and broad group of people.

Planned Seminars