In this talk, I hope to reflect on some of the progress made in the field of interpretable machine learning. We will reflect on where we are going as a field, and what are the things we need to be aware and be careful as we make progress. With that perspective, I will then discuss some of my recent work 1) sanity checking popular methods and 2) developing more lay person-friendly interpretability method.
Been Kim is a senior research scientist at Google Brain. Her research focuses on building interpretable machine learning - making ML understandable by humans for more responsible AI. The vision of her research is to make humans empowered by machine learning, not overwhelmed by it. She gave ICML tutorial on the topic in 2017, CVPR and MLSS at University of Toronto in 2018. She is a co-workshop Chair ICLR 2019, and has been an area chair and a program committee at NIPS, ICML, AISTATS and FAT* conferences. In 2018, she gave a talk at G20 meeting on digital economy summit in Argentina. In 2019, her work called TCAV received UNESCO Netexplo award for "breakthrough digital innovations with the potential of profound and lasting impact on the digital society". This work was also a part of CEO’s keynote at Google I/O 19'. She received her PhD. from MIT.
New York University
Knowledge generation through crowdsourcing is becoming increasingly possible and useful in many domain areas. Public health is a domain particularly suited to benefit from crowdsourced data, based on its focus on the multi-level factors related to health from daily life, outside of the clinic. In this talk I will discuss the work my group has done to understand how citizen-sourced data can be used in public health models of behavior and disease. While there are opportunities to provide high-resolution spatial and temporal views into public health phenomena, there are also challenges such as an often unknown population-at-risk (who is generating the data), the unstructured nature of crowdsourced data, and in understanding the data generating process behind how individuals generate health information. I will also discuss ongoing work in understanding how online crowdsourced data may synergize with physical world phenomena and potentially influence health.
Rumi Chunara is an Assistant Professor at NYU, jointly appointed at the Tandon School of Engineering (in Computer Science) and the College of Global Public Health (in Biostatistics/Epidemiology). Her research interests are in social computing and computational epidemiology; specifically in developing statistical and machine learning methodology for using observational data sources in population-level public health models. Her PhD is from the Harvard-MIT Division of Health, Sciences and Technology, Master’s degree from MIT in Electrical Engineering and Computer Science and Bachelor’s degree is in Electrical Engineering from Caltech with honors. She was named an MIT Technology Review Top 35 Innovator (2014), and selected for NSF Career, Gates Foundation Grand Challenges Exploration, and Facebook Research awards.
National Taiwan University
Jane Hsu is a Professor of Computer Science and Information Engineering at National Taiwan University, where she served as the Department Chair from 2011 to 2014. As the Director of the NTU IoX Center, Prof. Hsu is leading the research on Augmented Collective Beings to facilitate human-AI/IoT collaboration. Her research interests include multiagent systems, crowdsourcing, knowledge mining, commonsense computing, and smart IoT. She has been actively involved in AAAI, IEEE, and ACM conferences, and served as the President of Taiwanese Association for Artificial Intelligence in 2013-14. She received the 2016 MSRA Collaborative Research Award and Intel Labs Distinguished Collaborator Award.
Microsoft Research AI
Paul Bennett is a Sr Principal Researcher at Microsoft Research AI where he leads the Information & Data Sciences group. He was chair of the first HCOMP (2009) workshop that grew into the AAAI sponsored conference and has served on the HCOMP steering committee since its inception. His published research has focused on a variety of topics surrounding the use of machine learning in information retrieval – including ensemble methods and the combination of information sources, calibration, consensus methods for noisy supervision labels, active learning and evaluation, supervised classification and ranking, crowdsourcing, behavioral modeling and analysis, and personalization. Some of his work has been recognized with awards at SIGIR, CHI, and ACM UMAP as well as an ECIR Test of Time Honorable Mention award. Prior to joining MSR in 2006, he completed his dissertation in the Computer Science Department at Carnegie Mellon with Jaime Carbonell and John Lafferty. While at CMU, he also acted as the Chief Learning Architect on the RADAR project from 2005-2006 while a postdoctoral fellow in the Language Technologies Institute.
New York University
Panos Ipeirotis is a Professor and George A. Kellner Faculty Fellow at the Department of Technology, Operations, and Statistics at the Leonard N. Stern School of Business of New York University, and also an associated faculty member at the Center for Data Science and Computer Science departments. He got his Ph.D. degree in Computer Science from Columbia University in 2004. He has received ten “Best Paper” awards and nominations, a CAREER award from the National Science Foundation, and is the recipient of the 2015 Lagrange Prize in Complex Systems, for his contributions in the field of social media, user-generated content, and crowdsourcing.