Explainable and Transparent Artificial Intelligence and Multi-Agent Systems, 3rd International Workshop, EXTRAAMAS 2021, London, UK, May 7-8, 2021, Revised Selected Papers
| Type of publication: | Book |
| Citation: | |
| Year: | 2021 |
| Month: | July |
| Publisher: | Springer |
| URL: | https://link.springer.com/book... |
| Abstract: | Recent advancements in eXplainable Artificial Intelligence (XAI) are generating new understanding and opportunities. The increasingly complex intelligent agents/robots rely on often opaque machine learning-based algorithms. Explaining such mechanisms is a chief priority to enhance their acceptability, avoid failures, foster trust, and comply with relevant (inter)national regulations. The 2021 edition of the EXplainable and TRAnsparent AI and Multi-Agent Systems (EXTRAAMAS) workshop continues the successful track initiated in 2019 at Montreal and followed by the 2020 edition in New Zealand (which was virtual due to the COVID-19 pandemic circumstances). In particular, EXTRAAMAS 2021 set the following aims: (i) to strengthen the common ground for the study and development of explainable and understandable autonomous agents, robots, and Multi-Agent Systems (MAS), (ii) to investigate the potential of agent-based systems in the development of personalized user-aware explainable AI, (iii) to assess the impact of transparent and explained solutions on the user/agent behaviors, (iv) to discuss motivating examples and concrete applications in which the lack of explainability leads to problems, which would be resolved by explainability, and (v) to assess and discuss the first demonstrators and proof of concepts paving the way for the next generation of systems. EXTRAAMAS 2021 received 32 submissions. Each submission underwent a rigorous single-blind peer-review process (three to five reviews per paper). Eventually, 20 papers were accepted (19 full papers and 1 short paper), which are contained in this volume. Due to COVID-19 restrictions, the workshop and AAMAS (the hosting conference) were held online rather than in London, UK. For each paper, the authors performed live video presentations that, with their consent, are available on the EXTRAAMAS website1. Moreover, EXTRAAMAS 2021 included two keynotes: “Social and Ethical Responsibilities of Computing and the Role of Explainability and Transparency” given by Prof. Julie Shah and “Explainable Reasoning in the Face of Contradictions: From Humans to Machines” given by Prof. Emeritus Dov Gabbay, and two panels: the industrial panel “Explainable Agents - Escape from the Ivory Tower” and the panel dedicated to the European Project EXPECTATION which considers XAI in distributed and heterogeneous agent-based recommender systems. We would like to thank the industrial chair, publicity chairs, and Program Committee for their valuable work. We also thank the authors, presenters, and participants. Particular emphasis goes to Julie Shah and Dov Gabbay for their fantastic keynotes, and to Johanna Björklund, Tathagata Chakraborti, Kristijonas Cyras, Elizabeth Sklar, Andrea Omicini, Reyhan Aydogan, and Leon Van der Torre for their participation in very enthusiastic discussion panels. May 2021 Davide Calvaresi Amro Najjar Michael Winikoff Kary Främling |
| Keywords: | |
| Authors | |
| Editors | |
| Added by: | [] |
| Total mark: | 0 |
|
Attachments
|
|
|
Notes
|
|
|
|
|
|
Topics
|
|
|
|
|