Philip E. Bourne - University of Virginia
The Most Important Ten Simple Rules. The Ten Simple Rules series of professional development articles have been viewed millions of times. What are the most important rules and why?
Philip E. Bourne, PhD, FACMI is the Stephenson Dean of the School of Data Science, Professor of Data Science and Professor of Biomedical Engineering at the University of Virginia, USA. Prior to that he was the Associate Director for Data Science (ADDS; aka Chief Data Scientist) for the US National Institutes of Health (NIH) and a Senior Investigator at the National Center for Biotechnology Information (NCBI). In his role as ADDS he led the trans NIH US $110M per year Big Data to Knowledge (BD2K) research initiative and contributed to data policies and infrastructure aimed at accelerating biomedical discovery. Examples include: establishing the NIH Commons, support for data and software citation and establishing preprints as a supported form of research. Prior to joining NIH, Dr. Bourne was Associate Vice Chancellor for Innovation and Industry Alliances in the Office of Research Affairs and a Professor in the School of Pharmacy and Pharmaceutical Sciences at the University of California San Diego (UCSD). Dr. Bourne is a Past President of the International Society for Computational Biology, an elected fellow of the American Association for the Advancement of Science (AAAS), the International Society for Computational Biology (ISCB), the American Medical Informatics Association (AMIA) and the American Institute for Medical and Biological Engineering (AIMBE). He has published over 350 papers and 5 books garnering over 55,000 citations and co-founded 4 companies. Awards include the Jim Gray Award eScience Award and the Benjamin Franklin Award.
His current research focuses on data science methods applied to systems pharmacology structural bioinformatics and scholarly communication. He has a strong interest in helping the next generation through the Ten Simple Rules series of professional development articles and his work as Dean of one of the few data science schools worldwide where new models of higher education are being emphasized.
Kuan-lin Huang - Icahn School of Medicine at Mount Sinai
Search Optimization for a Fulfilling Career
Kuan-lin Huang, PhD is an Assistant Professor of Genetics and Genomic Sciences at Icahn School of Medicine at Mount Sinai in New York, USA. He grew up on the other side of the globe in Taiwan. He earned a B.A. from Wesleyan University, CT, USA with a High Honors dissertation in Molecular Biology & Biochemistry (yeast molecular genetics) and an Honors dissertation in Studio Art (conceptual installations). He then obtained a Ph.D. at Washington University in St. Louis, USA, where he first conducted statistical genomics research of Alzheimer’s disease with Dr. Alison Goate and subsequently joined Dr. Li Ding’s lab to study cancer genomics and proteomics. He started the Computational Omics Lab at the Department of Genetics and Genomic Sciences and Center for Transformative Disease Modeling at Mount Sinai in October 2018, continuing to fight against human disease and against my insatiable craving for dark chocolates at work.
14:00 - 14:05 Welcome
14:05 - 14:10 5-min Chat Roulette (Breakout rooms)
14:10 - 15:00 Keynote: The Most Important Ten Simple Rules Phil Bourne (University of Virginia)
15:00 - 15:10 10-min Chat Roulette (Breakout rooms)
15:10 - 15:40 Session 1: Methods
- MUMBO: MUlti-task Max-value Bayesian Optimisation Henry Moss, David Leslie and Paul Rayson
- Tree-based Learning for Dynamic Data Streams Christian Schreckenberger, Christian Bartelt and Heiner Stuckenschmidt
- Reducing Over-Confident Errors via Context-Aware Distributional Signatures Iftitahu Ni’Mah, Vlado Menkovski and Mykola Pechenizkiy
- Mining exceptional sequences using log likelihood based quality measures Rianne Schouten, Wouter Duivesteijn and Mykola Pechenizkiy
15:40 - 15:45 5-min Chat Roulette (Breakout rooms)
15:45 - 16:20 Session 2: Applications
- Learning to Simulate on Sparse Trajectory Data Hua Wei
- Detecting and predicting evidences of insider trading in the Brazilian market Filipe Lauar and Cristiano Arbex Valle
- Development of Natural Language Processing System for Analysing Free-text Sleep Diary Heereen Shim
- Learning to Detect Misinformation Using Meta-Learning Branislav Pecher, Ivan Srba and Maria Bielikova
- FlowFrontNet: Improving Carbon Composite Manufacturing with CNNs Simon Stieber, Niklas Schröter, Alexander Schiendorfer, Alwin Hoffmann and Wolfgang Reif
16:20 - 16:35 15-min break, with optional Chat Roulette (Breakout rooms)
16:35 - 17:25 Keynote Talk: Search Optimization for a Fulfilling Career Kuan-lin Huang (Ichan School of Medicine at Mount Sinai)
17:25 - 17:35 10-min Chat Roulette (Breakout rooms)
17:35 - 18:05 Session 3: Explainability
- Interpretable Dimensionally-Consistent Feature Extraction from Electrical Network Sensors Laure Crochepierre, Lydia Boudjeloud-Assala and Vincent Barbesant
- Machine Learning for Converting Black-Box Models to Interpretable Functions Sascha Marton, Christian Bartelt and Heiner Stuckenschmidt
- An uncertainty-based human-in-the-loop system for industrial tool wear analysis Alexander Treiss, Jannis Walk and Niklas Kuehl
- Regularized GLS Regression Mikko Niemi
18:05 - 18:10 Closing
18:10 - 19:00 (Zoom room stays open for those who would like to hang around and socialize)
For any additional questions, you can contact the PhD Forum Chairs (Marinka Zitnik and Robert West) at phd_chairs[at]ecmlpkdd2020.net.