Selected Tutorials

S.No.Tutorial Title
1DL4Code: Deep Learning for Programming, Compilers & Code Generation (Click Here!)
2 Fairness in Healthcare Machine Learning: A Practical Guide (Click Here!)
3Recent Advances in Pairwise Preference Learning (Click Here!)

1. DL4Code: Deep Learning for Programming, Compilers & Code Generation (download presentation slides here)

Speakers:

  • Sandya Mannarswamy, Independent NLP Researcher.
  • Dibyendu Das, Senior Principal Engineer, Intel.
  • Ramakrishna Upadrasta, Asst. Prof. IIT-Hyderabad.

Abstract:

Over the last few years, machine learning, in particular deep learning, has made great strides and has been successfully deployed in many real-world applications such as healthcare, customer care, finance, autonomous driving etc. One of the recent applications of deep learning has been in the area of software development and programming itself. Availability of large datasets of source code from various open-source platforms such as Github, StackOverflow etc have facilitated the application of ML/DL/NLP techniques to source code and its related artefacts, in various areas such as source code search, analysis and maintenance, compilers, program repair, automatic code generation etc. Also, DL-based encoding and optimization has been finding increasing traction among the compiler development and research community. However, work in this space has been largely siloed inside the software engineering and compiler research community and has mostly remained outside the focus of the mainstream ML/DL/NLP/KDD research conference venues.
This tutorial is intended to provide an in-depth overview of DL4Code at a major ML/DL/KDD research venue such as PAKDD so as to focus research attention and collaboration between SE and ML research communities in this emerging area. This tutorial provides a detailed overview of ML/DL/NLP techniques in programming, compilers and automatic source code generation covering models, applications and datasets. While there has been considerable progress in this area, a number of challenges still remain, especially in applying probabilistic techniques to applications which require deterministic correctness, interpretability and verifiability such as in compilers and automatic code generation. We discuss the various challenges involved in applying ML/DL/NLP techniques to compilers/code generation and also outline some of the future research directions. We believe that having this tutorial at PAKDD would be an important first step in facilitating increased research focus from mainstream ML/NLP community on this topic.

Speakers Bio

Sandya Mannarswamy is an independent NLP researcher. She was previously a senior research scientist at Conduent Labs India in the NLP research group. She holds a Ph.D. in computer science from Indian Institute of Science, Bangalore. Her research interests span natural language processing, machine learning and compilers. Her research career spans over 20 years, at various R&D labs, including Hewlett Packard Ltd, IBM Research etc. She has co-organized a number of workshops including workshops at International Conference on Data Management, Machine Learning Debates workshop at ICML-2018 etc. She holds a number of publications and patents.
Dr. Dibyendu Das is a Senior Principal Engineer at Intel where he works at the confluence of LLVM based compilation technology and AI. He has been associated with compiler technology, parallel computing and performance projections in several companies including IBM, HPE, AMD and Motorola for close to 25 years. He was the architect of AMD's AOCC compiler for its Zen-sever line that has held world-record SPEC scores in the last few years. Dr Das has been part of the program committee of several conferences and has organized sponsored workshops and LLVM BoFs. Dr. Das holds a PhD in Computer Science from IIT Kharagapur.
Dr. Ramakrishna Upadrasta is an Asst. Professor at IIT Hyderabad (IITH) where he has been since 2014. He leads the Scalable Compilers research group at IITH. He holds a Ph.D in Computer Science from University of Paris-Sud, France, and INRIA, Paris. He has M.S from Colorado State University, USA, an M.Tech in Computer Science from Indian Institute of Science (IISc), Bangalore and a B.E in Electrical and Electronics Engineering from Andhra University, Visakhapatnam. Prior to joining IITH, he was a visiting scientist at IISc, a research engineer at INRIA, Paris, a research scholar at Lawrence Livermore National Laboratories, USA, and a compiler engineer in Hewlett Packard. He has helped organize Student Research Symposiums at HiPC as well as polyhedral compilation workshops at HiPEAC.

2. Fairness in Healthcare Machine Learning: A Practical Guide (download presentation slides here)

Speakers:

  • Muhammad Aurangzeb Ahmad, Department of Computer Science, University of Washington Tacoma.
  • Dr. Carly Eckert, Department of Epidemiology, University of Washington.
  • Christine Allen, KenSci Inc, Seattle.
  • Vikas Kumar, KenSci Inc, Seattle.
  • Juhua Hu, Department of Computer Science, University of Washington Tacoma.
  • Ankur Teredesai, Department of Computer Science, University of Washington Tacoma.
  • Dr. Arpit Patel, Department of Bioinformatics and Medical Education, University of Washington.

Abstract:

The issue of bias and fairness in healthcare has been around for centuries. With the integration of AI in healthcare the potential to discriminate and perpetuate unfair and biased practices in healthcare increases many folds. The tutorial focuses on the challenges, requirements and opportunities in the area of fairness in healthcare AI and the various nuances associated with it. Healthcare as a multi-faceted systems level problem that necessitates careful consideration of different notions of fairness. In this tutorial we addresses this problem in the context of deploying machine learning models in the real world, and various challenges and opportunities that it presents the machine learning community.

Speakers Bio

Ankur Teredesai is a Professor in the Department of Computer Science at University of Washington Tacoma, and founder and director of the Center for Data Science at University of Washington. He is also the founder and CTO of KenSci, a vertical machine learning/AI healthcare informatics company focused on risk prediction in healthcare. Professor Teredesai has published more than 70 research papers in top machine learning and data mining conferences like KDD, AAAI, CIKM, SDM, PKDD etc. He is also the information officer of KDD.
Muhammad Aurangzeb Ahmad is a Research Scientist and Principal Data Scientist at KenSci Inc. a Machine learning/AI healthcare informatics company focused on risk prediction in healthcare. He is also Affiliate Associate Professor in the Department of Computer Science at University of Washington Tacoma. He has had academic appointments at University of Washington, Center for Cognitive Science at University of Minnesota, Minnesota Population Center and the Indian Institute of Technology at Kanpur. He has published more than 50 research papers in top machine learning and data mining conferences KDD, AAAI, SDM, PKDD etc.
Dr. Arpit Patel is a General Surgeon who graduated from residency training at The Brooklyn Hospital Center in NY. He is currently finishing the Clinical Informatics fellowship training program in the Department of Bioinformatics and Medical Education at the University of Washington in Seattle. Throughout his medical career, he has taken an interest in various aspects of healthcare informatics, including developing documentation and clinical decision support tools in the EHR and the theory and clinical applications of machine learning.
Vikas Kumar is a Data Scientist working at KenSci. In this role, Vikas works with a team of data scientists and clinicians to build consumable and trustable machine learning solutions for healthcare. His focus is in building explainable models in healthcare and application of recommendation systems in clinical settings. Vikas holds a Ph.D. with a major in Computer Science and minor in Statistics from the University of Minnesota, Twin Cities. He has worked on modeling and application of recommendation systems in various domains, such as media, location, and healthcare. His focus has been to interpret the balance users seek between known (or familiarity) and unknown (or novel) items to build adaptive recommendations. Prior to his Ph.D., he completed his Bachelor’s at the National Institute of Technology, India and worked as a software engineer in Microsoft India.
Dr. Carly Eckert MD, MPH, is the Medical Director of Clinical Informatics at KenSci Inc. In this role, Dr. Carly leads and works with doctors and data scientists to identify patterns in patient data to predict risk that can cost-effectively improve care outcomes. Prior to her role at KenSci, Dr. Carly was the associate medical director for catastrophic care at the Department of Labor and Industries for the state of Washington. Dr. Carly trained in General Surgery at Vanderbilt University Medical Center and in Occupational and Environmental Medicine and Preventive Medicine at the University of Washington (UW). She has also co-authored several publications on topics related to general surgery, occupational health, and occupational injury

3. Recent Advances in Pairwise Preference Learning (download presentation slides here)

Speakers:

  • Arun Rajkumar, Assistant Professor, Indian Institute of Technology, Madras.
  • Dev Yashpal Sheth, Undergraduate Student, Indian Institute of Technology, Madras.

Abstract:

Analysing preferences using pairwise ordered data has a long history and has been core to several research areas including machine learning, statistics, operations research, game theory, social choice and theoretical computer science with a range of applications including ad-placement, voting, sports ranking, multi-criteria decision making among several others. Research in each of the areas mentioned above have developed independently, typically, without a lot of interaction among them. The broad aim of this tutorial is to overview the exciting recent advances in preference learning with a focus on pairwise preference learning in passive, active, bandit and social choice related settings.

Speakers Bio

Arun Rajkumar is an assistant professor in the Department of Computer Science and Engineering at the Indian Institute of Technology, Madras. Prior to joining IIT Madras, he was a research scientist at Xerox research centre, India. His research areas include machine learning with a specific focus on ranking, statistical learning theory and sequential decision making. He has actively published in top AI/ML venues including ICML, NeurIPS, COLT, AAMAS, UAI, AAAI, etc.
Dev Yashpal Sheth is an undergraduate researcher in the Department of Computer Science and Engineering at the Indian Institute of Technology, Madras. He has worked as a research assistant at the Center for Data Science, New York University. His research interests include active/adaptive learning, deep learning and reinforcement learning and he has published in related areas.

Important Dates

Proposals due Feb 8, 2021,Mar 6, 2021
Tutorial notification Mar 26, 2021
Submission of tutorial notes Apr 12, 2021

*All deadlines are 23:59 Pacific Standard Time (PST)