accepted papers

Oral presentations

  • Attention-Based Prototypical Learning Sercan O. Arik (Google); Tomas Pfister (Google) [pdf]
  • Participatory Problem Formulation for Fairer Machine Learning Through Community Based System Dynamics Donald Martin, Jr. (Google); Vinodkumar Prabhakaran (Google); Jill Kuhlberg (Univ of North Carolina - Chapel Hill); Andrew Smart (Google Inc.); William Isaac (DeepMind) [pdf]
  • Using Simulated Data to Generate Images of Climate Change Mélisande Teng (Mila, Université de Montréal); Gautier Cosne (Mila, Université de Montréal); Adrien Juraver (Mila, Université de Montréal); Victor Schmidt (Mila, Université de Montréal); Vahe Vardanyan (Mila, Université de Montréal); Sasha Luccioni (Mila); Yoshua Bengio (Mila) [pdf]
  • DEEP LEARNING MOBILE APPLICATION TOWARDS MALARIA DIAGNOSIS Emilian A Ngatunga (University of Dodoma); Saidi Mmaka (University of Dodoma)
  • Getting a CLUE: A Method for Explaining Uncertainty Estimates Javier Antoran (University of Cambridge); Umang Bhatt (University of Cambridge); Tameem Adel (University of Cambridge); Adrian Weller (University of Cambridge); Jose Miguel Hernandez-Lobato (University of Cambridge) [pdf]

Poster presentations

  • Population Mapping in Informal Settlements with High-Resolution Satellite Imagery and Equitable Ground-Truth Konstantin Klemmer (University of Warwick); Godwin Yeboah (University of Warwick); João Porto de Albuquerque (University of Warwick); Stephen Jarvis (University of Warwick) [pdf]
  • Counterfactual Accuracies of Alternative Models Umang Bhatt (University of Cambridge); Adrian Weller (University of Cambridge); Muhammad Bilal Zafar (Bosch Center for Artificial Intelligence); Krishna Gummadi (MPI-SWS) [pdf]
  • Machine Learning for Digital Try-On Junbang Liang (University of Maryland, College Park); Ming Lin (UMD-CP & UNC-CH) [pdf]
  • RL AGENTS IMPLICITLY LEARNING HUMAN PREFERENCES Nevan Wichers (Google) [pdf]
  • Using competency questions to select optimal clustering structures for residential energy consumption patterns Wiebke Toussaint (University of Cape Town); Deshendran Moodley (University of Cape Town) [pdf]
  • LEVERAGING NATIONWIDE DATA AND DOMAIN EXPERTISE TO INFER CAUSAL EFFECT OF CESAREAN SECTION BIRTH ON LONG TERM PEDIATRIC HEALTH Ayya Keshet (Weizmann Institute of Science) [pdf]
  • Training Self-Driving Vehicles Using Transfer Learning and Simulated Accidents Shivam Akhauri (University of Maryland College Park); Laura Zheng ( University of Maryland College Park); Ming Lin (UMD-CP & UNC-CH) [pdf]
  • Autonomous Driving in Dense Urban Scenarios: Recent Progress and Challenges Rohan Chandra (University of Maryland); Uttaran Bhattacharya (University of Maryland, College Park); Trisha Mittal (University of Maryland); Aniket Bera (University of Maryland, College Park); Dinesh Manocha (UMD) [pdf]
  • TOWARDS CLASSIFICATION PARITY ACROSS COHORTS Aarsh Patel (University of Massachusetts Amherst); Rahul Gupta (Amazon); Mukund Sridhar (Amazon); Satyapriya Krishna (Amazon.com); Alok Aman (Amazon); Peng Liu (Amazon) [pdf]
  • Identifying Interpretable Word Vector Subspaces with PCA Jessica Zhao (Harvard University); Bill Zhang (Harvard University) [pdf]
  • Active Learning for Efficient Construction of Diverse Biobanks Daniel Mas Montserrat (Purdue University); Carlos Bustamante (Stanford University); Alexander Ioannidis (Stanford University) [pdf]
  • Adaptive Prediction Timing for Electronic Health Records Jacob T Deasy (University of Cambridge) [pdf]
  • Egoshots, an ego-vision life-logging dataset and semantic fidelity metric to evaluate diversity in image captioning models Pranav Agarwal (INRIA RITS); Betancourt Alejandro (Eindhoven University of Technology); Vana Panagiotou (Philips Research); Natalia Diaz Rodriguez (ENSTA Paris and INRIA Flowers) [pdf]
  • Real world applications of machine learning require new strategies for anticipating out of distribution data Bernease R Herman (University of Washington) [pdf]
  • Concrete Problems in AI Safety, Revisited Deborah I Raji (University of Toronto); Roel Dobbe (AI Now Insitute, New York University) [pdf]