Award Paper Presentation Instructions:

Presentation slides for 30 min (20 min presentation + 10 min Q&A). 

Spotlight (Oral) Paper Presentation Instructions:

Presentation slides for 15 min (12 min presentation + 3 min Q&A)

Poster Paper Presentation Instructions:

Posters can be created in a PDF format, on a page size of up to A0 (33.1 x 46.8 inches). Landscape orientation is preferred. Authors should print the posters (as per standard protocols of poster printing, You can order a poster to be printed using CMU’s Tartan Ink service) and present them at the workshop venue during the poster session. 

Online Oral and Poster Paper Presentation Instructions:

Oral: For authors presenting online, send us your slides and video presentation (@epistemicai.eu@gmail.com) of above mentioned time slot.

Posters: For authors presenting posters in an online manner kindly send us your video presentation (10 min) and PDF of your poster @epistemicai.eu@gmail.com with your paper ID and title. For each poster paper, total time is 12 min (10 min video presentation + 2 min Q&A). 

The E-pi UAI 2023 aims to raise awareness around the modelling of Epistemic Uncertainty in AI/ML, a rapidly emerging topic in the AI community represented at UAI. As we aim for the broadest possible involvement, we plan to invite the submission of peer-reviewed papers covering the following topics: 

• Model uncertainty estimation,

• Robustness to distribution shift, 

• Out-of-distribution generalisation, 

• Model adaptation, 

• Datasets and protocols for evaluating uncertainty and robustness, 

• Conformal prediction, 

• Distribution-free uncertainty quantification, 

• Optimisation under uncertainty, 

• Uncertainty estimation using deep ensembles, 

• Bayesian deep learning (approximate inference, Bayesian deep RL), 

• Deep recognition models for variational inference, 

• Epistemic learning, 

• Uncertainty in real-world applications (e.g. autonomous driving, healthcare, language models). 

The list is not exhaustive as we wish to mobilize the whole community around this theme.

We encourage you to freely submit your papers to other venues of your choice, including any preliminary work you may have. Our primary aim is to showcase advancements in the field of uncertainty in machine learning. We eagerly seek to highlight novel contributions and cutting-edge research in this area. 

We will award prizes for the best paper and the best student paper, and authors submitting original work will be invited to consider publication in a proceedings volume, subject to attracting a sufficient number of high-quality papers. The submission is non-archival, we will seek the consent of the authors before the proceedings.

The E-pi UAI 2023 workshop will follow the paper submission format of the UAI conference. Therefore, Papers must be submitted as a PDF file and are limited to 8 pages in length, including all figures and tables. At most two additional pages containing only references are allowed. For details concerning the format of the papers, please see the Submission Instructions. Papers that are overlength or violate the UAI proceedings format will be rejected without review. If you include supplementary material, please do not use packages like 'xr' to reference results or equations from the supplement in the main manuscript. Doing this will mean that your paper will not compile when it comes to being published. You may use such packages to put references in the supplementary material to refer to the main manuscript. (The camera-ready version of accepted pages can be up to 9 pages long, plus two additional pages containing only references, to allow authors to incorporate comments from the reviewing process.)

Accessibility and Inclusiveness

We kindly ask all authors to follow our guidelines for writing accessible papers. In particular, we expect that authors (1) review guidelines for accessibility to color-blind and visually impaired; (2) ensure their bibliography is up-to-date, including up-to-date names and venues; (3) use inclusive and respectful language throughout when talking about people.

Double-Blind Reviewing

Reviewing for E-pi UAI 2023 Workshop is double-blind, so you must make sure that the submission (including all supplementary material) does not disclose author identities or affiliations. Hence, among other precautions, you should use the third person to refer to your own work, you should not include names in the acknowledgements, detailed information about grants, and links to external resources that may reveal your identity or institution are forbidden.

Supplementary Material

For submission, supplementary material should be included in a separate file from the main paper. The entire file should be at most 10MB in size. Please use the template included for the supplementary material. You may use a package such as 'xr' to reference labels defined in your main manuscript.

You may also provide further supplementary material, such as source code or data, in a ZIP file of up to 50MB in size. In order to submit this, you must first upload your main submission, and you will then be able to upload the supplementary material from the author console.

Please note that reviewers primarily base their assessment on the main paper. They are not required to consider any supplementary material.

Submission Link

Papers Should be submitted on CMT at:  cmt3.research.microsoft.com/EpiUAI2023 

For further inquiries, please feel free to email us at epistemicai.eu@gmail.com.

Camera Ready Instructions:

Authors should submit the revised PDFs of their paper and supplementary (optional) at CMT on the given deadline. The UAI template for the final camera-ready version should be modified as "paper accepted at E-pi UAI workshop" 

• • • Joint Modelling for Uncertainty Quantification

Chunlin Ji (Kuang-Chi)*; Dingwei Gong (Sun Yat-sen University); Meiying Zhang (SUSTech)

• • • MiDAS: Domain Learning for Robust Fake News Detection in Distribution Shifts

Abhijit Suprem (Georgia Institute of Technology)*; Calton Pu (Georgia Tech)

• • • URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

Michael Kirchhof (University of Tübingen)*; Bálint Mucsányi (University of Tübingen); Seong Joon Oh (Naver AI Lab); Enkelejda Kasneci (University of Tuebingen)

• • • Massively Parallel Reweighted Wake-Sleep

Thomas E Heap (University of Bristol)*; Gavin Leech (University of Bristol); Laurence Aitchison (University of Bristol)

• • • EnSolver: Uncertainty-Aware CAPTCHA Solver Using Deep Ensembles

Duc C Hoang (Florida International University)*; Cuong V Nguyen (Florida International University); Amin Kharraz (Florida International University

• • • Deep learning and MCMC with aggVAE for shifting administrative boundaries: mapping malaria prevalence in Kenya

Elizaveta Semenova (University of Oxford)*; Swapnil Mishra (Imperial College London); Samir Bhatt (Imperial College London); Seth Flaxman (Oxford); H Juliette T Unwin (Imperial College London)

• • • Bag of Policies for Distributional Deep Exploration

Asen Nachkov (Imperial College London); Luchen Li (Imperial College London); Giulia Luise (Imperial College London); Filippo Valdettaro (Imperial College London); Aldo Faisal (Imperial College London)*

• • • Fair Ranking under Disparate Uncertainty

Richa Rastogi (Cornell)*; Thorsten Joachims (Cornell)

• • • A Novel Bayes’ Theorem for Upper Probabilities

Michele Caprio (University of Pennsylvania)*; Yusuf Sale (University of Munich (LMU)); Eyke Hüllermeier (University of Munich); Insup Lee (University of Pennsylvania)

• • • Defensive Perception: Estimation and Monitoring of Neural Networks Performance under Deployment

Hendrik Vogt (ZF Friedrichshafen AG)*; Mark Schutera (ZF Friedrichshafen AG); Stefan Bühler (ZF)

• • • Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet

Gonzalo Martínez (University Carlos III of Madrid)*; Lauren Watson (The University of Edinburgh); Pedro Reviriego (Reviriego); Jose Alberto Hernandez (Universidad Carlos III de Madrid); Marc Juarez (The University of Edinburgh); Rik Sarkar (The University of Edinburgh)

• • • Model Robustness and Active Learning with Missing-Not-At-Random Outcomes

Alan Mishler (J.P. Morgan Chase)*; Mohsen Ghassemi (JP Morgan Chase); Alec Koppel (JP Morgan Chase); Sumitra Ganesh (JPMorgan)

• • • Nadaraya-Watson Selective Regression

Fedor Noskov (Skoltech); Alexander Fishkov (Skoltech); Maxim Panov (Technology Innovation Institute)

• • • Optimizing Brain Tumor Classification: A Comprehensive Study on Transfer Learning and Imbalance Handling in Deep Learning Models

Raza Imam (Aligarh Muslim University)*; Mohammed Talha Alam (Jamia Hamdard University)

• • • Offline Reinforcement Learning with Pessimistic Value Priors

Filippo Valdettaro (Imperial College London)*; Aldo Faisal (Imperial College London)

•  Semantic Attribution For Explainable Uncertainty Quantification

Hanjing Wang (Renselaer Polytechnic Institute)*; Dhiraj Joshi (IBM Research AI); Shiqiang Wang (IBM Research); Qiang Ji (Renselaer Polytechnic Institute)