AAAI 2019 Fall Symposium Series - Westin Arlington Gateway in Arlington, VA, USA, November 7–9, 2019
Human-centered AI: Trustworthiness of AI Models & Data
Join & Register here!
To facilitate the widespread acceptance of AI systems guiding decision-making in real-world applications, it is key that solutions comprise trustworthy, integrated human-AI systems. Not only in safety-critical applications such as autonomous driving or medicine, but also in dynamic open world systems in industry and government it is crucial for predictive models to be uncertainty-aware and yield well-calibrated (and thus trustworthy) predictions for both in-domain samples ("known unknowns") as well as out-of-domain samples ("unknown unknowns"). Another key requirement for deployment of AI at enterprise scale is to realize the importance of integrating human-centered design into AI systems such that humans are able to use systems effectively, understand results and output, and explain findings to oversight committees.
While the focus of this symposium is on AI systems to improve data quality and technical robustness and safety, we welcome submissions from broadly defined areas also discussing approaches addressing requirements such as explainable models, privacy, fairness, transparency and accountability.
- Human-Centered AI
- Data Quality
- Trustworthy AI
- Ethical AI
- Explainable AI
- Bayesian Deep Learning
- Uncertainty Quantification
- Probabilistic Machine Learning
- Testing approaches to neural networks
- Continuous monitoring of AI systems
- Causal Explainability
- Cause and Effect Relationships
Join & Register here!
Thursday, November 7th 2019
8:50 am - 9:00 am
Welcome (all)
9:00 am - 10:30 am - (10 min + 20 discussion/Q&A)
Session #1 - Point of View Panel
- Paper 42: Richard Benjamins, Alberto Barbado González and Daniel Sierra Ramos: Responsible AI by Design in Practice
- Paper 87: Ryan Wisnesky and Eric Daimler: Informal Data Transformation Considered Harmful
- Paper 137: Nader Sehatbakhsh, Ellie Daw, Onur Savas, Amin Hassanzadeh and Ian McCulloh: Security and Privacy Considerations for Machine Learning Models Deployed in the Government and Public Sector
10:30 am - 11:00 am
Coffee Break
11:00 am - 12:00 pm - (45 min + 15 min)
Invited Talk #1:
Markus Kaiser, Siemens Corporate Technology, Germany: Learning in the Physical World
12:00 pm - 1:30 pm
Lunch Break
1:30 pm - 3:30 pm (25 min + 5 min)
Session #2 - Quality
- Paper 48: Hiba Arnout, Johannes Kehrer, Johanna Bronner and Thomas Runkler: Visual Evaluation of Generative Adversarial Networks for Time Series Data
- Paper 51: Tsung-Yen Yang, Justinian Rosca, Karthik Narasimhan and Peter Ramadge: Projection Based Constrained Policy Optimization
- Paper 84: Joseph Nassar, Marc Bosch, Viveca Pavon-Harr and Ian McCulloh: Assessing Data Quality of Annotations With Krippendorff's Alpha For Applications in Computer Vision
- Paper 71: Kasra Mokhtari and Alan Richard Wagner: The Pedestrian Patterns Dataset
3:30 pm - 4:00 pm
Coffee Break
4:00 pm - 5:00 pm - (45 min + 15 min)
Invited Talk #2
Dr. Gil Alterovitz, Director of Artificial Intelligence for the U.S. Veterans Administration and former Presidential Innovation Fellow in the White House
6:00 pm - 7:00 pm
AAAI Symposium Reception
Friday, November 8th 2019
9:00 am - 10:30 am - (25 min + 5 min)
Session #3 - Explain
- Paper 21: Wei Li, Chunchen Liu, Zhi Geng and John Murray: Causal Mediation Analysis with Multiple Treatments and Latent Confounders
- Paper 36: Marcel Hildebrandt, Jorge Quintero Serna, Yunpu Ma, Martin Ringsquandl, Mitchell Joblin and Volker Tresp: Debate Dynamics for Human-comprehensible Fact-checking on Knowledge Graphs
- Paper 94: Daoming Lyu, Fangkai Yang, Steven Gustafson and Bo Liu: A Joint Planning and Learning Framework for Human-Aided Decision-Making
10:30 am - 11:00 am
Coffee Break
11:00 am - 12:00 pm - (45 min + 15 min)
Invited Talk #3
Rediet Abebe (Harvard)
12:00 pm - 1:30 pm
Lunch Break
1:30 pm - 2:30 pm - (45 min + 15 min)
Invited Talk #4
Dr. Daniel Sonntag, Director of the Interactive Machine Learning Lab, German Research Center for Artificial Intelligence (DFKI): Interactive Machine Learning and Explainable AI, two sides of the same coin.
2:30 pm - 3:30 pm - (25 min +5 min)
Session #4 - Human Trust
- Paper 43: Maryam Ashoori and Justin Weisz: Trustworthiness of AI-infused Decision-Making Processes
- Paper 44: John Licato, Zaid Marji and Sophia Abraham: Scenarios and Recommendations for Ethical Interpretive AI
- Paper 85: Bogdana Rakova and Rumman Chowdhury: Human self-determination within algorithmic sociotechnical systems
3:30 pm - 4:00 pm
Coffee Break
4:00 pm - 5:00 pm - (45 min + 15 min)
Invited Talk #5
Dr. Eric Daimler, Former White House (Obama Administration) Director for AI & Robotics; current CEO of Spinglass
1 x Talk
6:00 pm - 7:00 pm
AAAI Plenary Session
The symposium will include invited talks, presentations of work in progress and completed work, a demo/poster section with showcases for new advances and an open panel discussion focusing on key issues at the end. Authors of accepted papers are encouraged to also provide a poster or a demo in order to facilitate a more interactive presentation of their work.
Both regular papers (6-8 pages not including references) and short papers (2-4 pages) will be considered. All papers have to be submitted in PDF format; camera-ready versions must be formatted according to the AAAI guidelines.
Submission and reviewing will be via EasyChair: https://easychair.org/conferences/?conf=fss19
- Paper (full and short) submission deadline: July 26 | Due to multiple request, we extend the deadline to August 4th
- Paper notifications: August 16 | Due to deadline extension, paper notificatiion will be send out at August 25th
- Final camera-ready papers due: September 13
- Registration deadline: September 20
The AAAI 2019 Fall Symposium Series will be held at the Westin Arlington Gateway in Arlington, VA. Registration and hotel details from AAAI are here.
Join & Register here!
- Florian Buettner, Siemens AI, Germany, buettner.florian@siemens.com
- John Piorkowski, Whiting School of Engineering, USA, jpiorko2@jhu.edu
- Ian McCulloh, Accenture Federal Services, USA ian.mcculloh@accenturefederal.com
- Ulli Waltinger, Siemens AI, Germany, ulli.waltinger@siemens.com
- Tarek R. Besold, Alpha Health AI Lab, Spain, tarek.besold@telefonica.com
- Christian Guttmann, Tieto AI & Karolinska Institute, Sweden, guttmann.public@gmail.com
- Melih Kandemir, Bosch Center for AI, Germany, Melih.Kandemir@de.bosch.com
- Carl Henrik Ek, University of Bristol, UK and Royal Institute of Technology, UK/Sweden, carlhenrik.ek@bristol.ac.uk
- Stoney Trent, U.S. Joint Artificial Intelligence Center
- Neil Johnson, George Washington University, USA.
- Kevin Chan, Army Research Laboratory, USA.
- Ananthram Swami, Army Research Laboratory, USA
- Marc Bosch-Ruiz, Accenture, USA
- Kathleen Carley, Carnegie Mellon University, USA
- John Skvoretz, University of South Florida, USA
- Doug Lange, Computer Scientist at Space and Naval Warfare System Center, Pacific, USA
- Andreas Holzinger, University of Graz, Austria
- Nicolas Vayatis, ENS Paris-Saclay, France
- Harald Kosch, University Passau, Germany
- Derek Doran, Wright State University, US
- Kristian Lum, Human Rights Data Analysis Group (HRDAG), US
- Chris Biemann, University of Hamburg, Germany
- Justinian Rosca, Siemens Princeton US
- Roberto Confalonieri, Alpha Health AI Lab, Spain
- Rumman Choudhurry, Accenture, USA