Dear colleagues, Please consider participating in the following workshop at this year's ECML PKDD conference.
*Uncertainty meets Explainability in Machine Learning *- Tutorial & Workshop (Combined Event) @ *ECML-PKDD 2023* (European Conference in Machine Learning) Turin, Italy, September 18-22, 2023 https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fxai-uncertainty.github.io%2F&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880445144%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=bt1t2V4aAVNO0XO%2FoM0FF0i7DmI3jdt1FBug77aMLrE%3D&reserved=0 https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fcmt3.research.microsoft.com%2FECMLPKDDworkshop2023%2FTrack%2F3%2FSubmission%2FCreate&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880445144%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=TjuArZvwcKet7LmfVjNB%2FqzUfX0lLqtJVDYFHhJlBJo%3D&reserved=0 *** *Call for papers* <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fxai-uncertainty.github.io%2Fcfp%2F&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=pg2sDJfiIs6dY0YnzgRdojoUJ4GskJnQxuorhNr4998%3D&reserved=0> *** * Paper submission due June 12, 2023 * Acceptance notification due July 12, 2023 * Event @ ECML-PKDD 2023: September 22, 2023 ----------------------------------------------------------------------------------------- Machine learning systems have become increasingly popular in crucial high-stakes fields, such as healthcare and finance. To be effective in these domains, the models must not only make precise predictions but also provide relevant explanations for those predictions. To achieve this goal, there has been a substantial research effort in recent years to develop techniques that explain black-box models and create models that are interpretable by design. Simultaneously, there is a growing emphasis on machine learning models that account for uncertainty. Decision-making systems can encounter uncertainties stemming from different origins, each offering a distinct perspective. For instance, aleatoric uncertainty arises from the inherent randomness of the prediction, while epistemic uncertainty arises from the insufficient amount of data. In general, incorporating uncertainty enhances a model’s reliability by allowing it to acknowledge scenarios where it lacks the necessary knowledge to make an accurate prediction. The intersection of explainability and uncertainty has drawn attention for its potential to combine these domains towards Trustworthy ML. Some notable innovative approaches include: developing interpretability methods for probabilistic models, quantifying the uncertainty of explanations, and explaining the sources of uncertainty. The primary goal of this full-day event, consisting of a Tutorial and a Workshop, is to jointly explore how explainability and uncertainty can be leveraged to build robust and trustworthy AI systems. The tutorial (morning session) will establish the foundation for (a) uncertainty modelling and (b) explainability in machine learning. Then, the workshop (afternoon session) will delve into innovative techniques at the intersection of these two domains. ------------------------------------------------------------------------------------------ We invite submissions from researchers interested in Interpretable Machine Learning (IML) and/or Uncertainty Quantification, for our Workshop. The scope of the topics covers all types of data (tabular, text, images, etc.) and all types of ML models. We particularly encourage interdisciplinary work that lies on the intersection of explainability and uncertainty. The workshop’s topics of interest include (but not limited to) methods and applications on: - Intersection of Explainability and Uncertainty: - Explainability methods that produce uncertain explanations - Explainability for probabilistic ML models - Explainability on Bayesian Models - Explainability on Ensemble Methods - Identifying and explaining the sources of uncertainty - Interpretable-by-design models that incorporate uncertainty - Explainability: - XAI and IML (Interpretable Machine Learning) - Counterfactual Explanations - Global and Local Explainability Techniques - Interpretable-by-design models - Adversarial Attacks on explainability methods - Stability of explainability methods - AI model robustness and explainability - Explaining trade-offs between objectives, such as effectiveness, bias, uncertainty - Explainability and privacy - Explainability and fairness ----------------------------------------------------------------------------------------- *** *Submission guidelines **** - *Full Papers:* Suitable for novel contributions related to Explainability and/or Uncertainty. This can include a novel method or new insights on these two fields that would be valuable for the community. Please note that the page limit for the paper is 14 pages, excluding references. - *Extended Abstracts:* Suitable for discussing novel ideas related to Explainability and/or Uncertainty. This can include open research challenges or industrial applications to foster discussion among panelists and facilitate future collaborations. The page limit for the extended abstract is 2-4 pages, excluding references. - *Abstracts of already published work:* Suitable for discussing previously published work related to Explainability and/or Uncertainty. The page limit for the extended abstract is 2, excluding references. Post-workshop proceedings will be published by Springer Communications in Computer and Information Science <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.springer.com%2Fseries%2F7899&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=ovl3z9u%2FP%2FOzqrvAcpG1X9Hzu5d1czW2KQKkjIfBu54%3D&reserved=0>. They will be organized by focused scope and possibly indexed by WOS. However, authors can choose *to opt-in or opt-out*. ----------------------------------------------------------------------------------------- *** *Organizing Committee **** Workshop: Vasilis Gkolemis <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fgivasile.github.io%2F&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=MBB8P94mwsTMRZLyJNL23HJeqRf8ZeRIc2V2PbtF6UY%3D&reserved=0>, Harokopio University of Athens, Greece Christos Diou <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdiou.github.io%2F&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=xTWBfg9BmjMhw40rGcTtRYnLkNo3eqdxnIUSOecpc1Y%3D&reserved=0>, Harokopio University of Athens, Greece Tutorial: Viktor Bengs <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.kiml.ifi.lmu.de%2Fpeople%2Fpostdocs%2Fbengs%2Findex.html&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=vddbB8w5w9wKYMG8f%2FFPRfkA4hfltOLjydOvNsossgQ%3D&reserved=0>, LMU, Germany Eyke Hullermeier, <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.mathematik-informatik-statistik.uni-muenchen.de%2Fpersonen%2Fprofessoren%2Fhuellermeier%2Findex.html&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=XIDt0gHsoH0KGZfcjGEykii%2BJeAyMvuoevItuffroSQ%3D&reserved=0> LMU, Germany Willem Waegeman <https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.ugent.be%2Fdass%2Fen%2Fresearch%2Fwaegeman&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=zW7wXfb7oL1Cq%2F2VPoThZ3DpY0RWTM9CsrUdlqv7q68%3D&reserved=0>, Ghent University, Belgium -- Dr. Christos Diou Assistant Professor Department of Informatics and Telematics Harokopio University of Athens Omirou 9, Athens, 17778, GREECE T : +30-210-9549-449 W: https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdiou.github.io%2F&data=05%7C01%7Cuai%40engr.orst.edu%7C23650acfc8834d51acc208db51ec9a6c%7Cce6d05e13c5e4d6287a84c4a2713c113%7C0%7C0%7C638193848880601358%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=xTWBfg9BmjMhw40rGcTtRYnLkNo3eqdxnIUSOecpc1Y%3D&reserved=0
_______________________________________________ uai mailing list uai@engr.orst.edu https://it.engineering.oregonstate.edu/mailman/listinfo/uai