January 27th, 10:30 AM – 11:30 AM
Session 1: Algorithmic Fairness
Chair: Gillian Hadfield
Active Fairness in Algorithmic Decision Making
Michiel Bakker, Alejandro Noriega-Campero, Bernardo Garcia-Bulle and Alex Pentland
Paradoxes in Fair Computer-Aided Decision Making
Andrew Morgan and Rafael Pass
Fair Transfer Learning with Missing Protected Attributes
Amanda Coston, Karthikeyan Natesan Ramamurthy, Dennis Wei, Kush Varshney, Skyler Speakman, Zairah Mustahsan and Supriyo Chakraborty
How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness
Nripsuta Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David Parkes and Yang Liu
Posters for this session will be presented on January 27th at 7pm
Michiel Bakker, Alejandro Noriega-Campero, Bernardo Garcia-Bulle and Alex Pentland
Paradoxes in Fair Computer-Aided Decision Making
Andrew Morgan and Rafael Pass
Fair Transfer Learning with Missing Protected Attributes
Amanda Coston, Karthikeyan Natesan Ramamurthy, Dennis Wei, Kush Varshney, Skyler Speakman, Zairah Mustahsan and Supriyo Chakraborty
How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness
Nripsuta Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David Parkes and Yang Liu
Posters for this session will be presented on January 27th at 7pm
January 27th, 11:30 AM – 12:30 AM
Session 2: Norms and Explanations
Chair: Vincent Conitzer
Learning Existing Social Conventions via Observationally Augmented Self-Play (Best Paper Award)
Alexander Peysakhovich and Adam Lerer
Legible Normativity for AI Alignment: The Value of Silly Rules
Dylan Hadfield-Menell, Mckane Andrus and Gillian Hadfield
TED: Teaching AI to Explain its Decisions
Noel Codella, Michael Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush Varshney, Dennis Wei and Aleksandra Mojsilovic
Understanding Black Box Model Behavior through Subspace Explanations
Himabindu Lakkaraju, Ece Kamar, Rich Caruana and Jure Leskovec
Posters for this session will be presented on January 27th at 7pm
Alexander Peysakhovich and Adam Lerer
Legible Normativity for AI Alignment: The Value of Silly Rules
Dylan Hadfield-Menell, Mckane Andrus and Gillian Hadfield
TED: Teaching AI to Explain its Decisions
Noel Codella, Michael Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush Varshney, Dennis Wei and Aleksandra Mojsilovic
Understanding Black Box Model Behavior through Subspace Explanations
Himabindu Lakkaraju, Ece Kamar, Rich Caruana and Jure Leskovec
Posters for this session will be presented on January 27th at 7pm
January 27th, 2:00 PM – 3:00 PM
Session 3: Artificial Agency
Chair: Shannon Vallor
Shared Moral Foundations of Embodied Artificial Intelligence*
Joe Cruz
Building Jiminy Cricket: An Architecture for Moral Agreements Among Stakeholders
Beishui Liao, Marija Slavkovik and Leendert van der Torre
AI + Art = Human*
Antonio Daniele and Yi-Zhe Song
Speaking on Behalf: Representation, Delegation, and Authority in Computational Text Analysis
Eric Baumer and Micki McGee
Posters for this session will be presented on January 28th at 10am
* Papers without poster presentation
Joe Cruz
Building Jiminy Cricket: An Architecture for Moral Agreements Among Stakeholders
Beishui Liao, Marija Slavkovik and Leendert van der Torre
AI + Art = Human*
Antonio Daniele and Yi-Zhe Song
Speaking on Behalf: Representation, Delegation, and Authority in Computational Text Analysis
Eric Baumer and Micki McGee
Posters for this session will be presented on January 28th at 10am
* Papers without poster presentation
January 27th, 3:00 PM – 4:00 PM
Session 4: Autonomy and Lethality
Chair: Ryan Calo
Killer Robots and Human Dignity*
Daniel Lim
Regulating Lethal and Harmful Autonomy: Drafting a Protocol VI of the Convention on Certain Conventional Weapons*
Sean Welsh
Balancing the Benefits of Autonomous Vehicles
Timothy Geary and David Danks
Compensation at the Crossroads: Autonomous Vehicles and Alternative Victim Compensation Schemes
Tracy Pearl
Posters for this session will be presented on January 28th at 10am
Daniel Lim
Regulating Lethal and Harmful Autonomy: Drafting a Protocol VI of the Convention on Certain Conventional Weapons*
Sean Welsh
Balancing the Benefits of Autonomous Vehicles
Timothy Geary and David Danks
Compensation at the Crossroads: Autonomous Vehicles and Alternative Victim Compensation Schemes
Tracy Pearl
Posters for this session will be presented on January 28th at 10am
January 27th, 4:30 PM – 5:00 PM
Session 5: Rights and Principles
Chair: Shannon Vallor
The Role and Limits of Principles in AI Ethics: Towards a Focus on Tensions
Jess Whittlestone, Rune Nyrup, Anna Alexandrova and Stephen Cave
How Technological Advances Can Reveal Rights
Jack Parker and David Danks
Posters for this session will be presented on January 28th at 10am
Jess Whittlestone, Rune Nyrup, Anna Alexandrova and Stephen Cave
How Technological Advances Can Reveal Rights
Jack Parker and David Danks
Posters for this session will be presented on January 28th at 10am
January 28th, 10:30 AM – 11:30 PM
Session 6: Social Science Models for AI
Chair: Susan Athey
Invisible Influence: Artificial Intelligence and the Ethics of Adaptive Choice Architectures*
Daniel Susser
Reinforcement learning and inverse reinforcement learning with system 1 and system 2
Alexander Peysakhovich
Incomplete Contracting and AI Alignment
Dylan Hadfield-Menell and Gillian Hadfield
Theories of parenting and their application to artificial intelligence*
Sky Croeser and Peter Eckersley
Posters for this session will be presented on January 28th at 4pm
* Papers without poster presentation
Daniel Susser
Reinforcement learning and inverse reinforcement learning with system 1 and system 2
Alexander Peysakhovich
Incomplete Contracting and AI Alignment
Dylan Hadfield-Menell and Gillian Hadfield
Theories of parenting and their application to artificial intelligence*
Sky Croeser and Peter Eckersley
Posters for this session will be presented on January 28th at 4pm
* Papers without poster presentation
January 28th, 11:30 AM – 12:30 PM
Session 7: Measurement and Justice
Chair: David Danks
Actionable Auditing: Investigating the Impact of Publicly Naming Biased Performance Results of Commercial AI Products (Best Student Paper Award)
Inioluwa Deborah Raji and Joy Buolamwini
A framework for benchmarking discrimination-aware models in machine learning
Rodrigo L. Cardoso, Wagner Meira Jr., Virgilio Almeida and Mohammed J. Zaki
Towards a Just Theory of Measurement: A Principled Social Measurement Assurance Program*
Thomas Gilbert and McKane Andrus
Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Allison Woodruff, Christine Luu, Pierre Kreitmann, Jonathan Bischof and Ed H. Chi
Posters for this session will be presented on January 28th at 4pm
Inioluwa Deborah Raji and Joy Buolamwini
A framework for benchmarking discrimination-aware models in machine learning
Rodrigo L. Cardoso, Wagner Meira Jr., Virgilio Almeida and Mohammed J. Zaki
Towards a Just Theory of Measurement: A Principled Social Measurement Assurance Program*
Thomas Gilbert and McKane Andrus
Putting Fairness Principles into Practice: Challenges, Metrics, and Improvements
Alex Beutel, Jilin Chen, Tulsee Doshi, Hai Qian, Allison Woodruff, Christine Luu, Pierre Kreitmann, Jonathan Bischof and Ed H. Chi
Posters for this session will be presented on January 28th at 4pm
January 28th, 2:00 PM – 3:00 PM
Session 8: AI for Social Good
Chair: Vincent Conitzer
On Influencing Individual Behavior for Reducing Transportation Energy Expenditure in a Large Population
Shiwali Mohan, Frances Yan, Victoria Bellotti, Ahmed Elbery, Hesham Rakha and Matthew Klenk
Guiding Prosecutorial Decisions with an Interpretable Statistical Model
Zhiyuan Lin, Alex Chohlas-Wood and Sharad Goel
Using deceased-donor kidneys to initiate chains of living donor kidney paired donations: algorithm and experimentation
Cristina Cornelio, Lucrezia Furian, Antonio Nicolò and Francesca Rossi
Inferring Work Task Automatability from AI Expert Evidence
Paul Duckworth, Logan Graham and Michael Osborne
Posters for this session will be presented on January 28th at 4pm
Shiwali Mohan, Frances Yan, Victoria Bellotti, Ahmed Elbery, Hesham Rakha and Matthew Klenk
Guiding Prosecutorial Decisions with an Interpretable Statistical Model
Zhiyuan Lin, Alex Chohlas-Wood and Sharad Goel
Using deceased-donor kidneys to initiate chains of living donor kidney paired donations: algorithm and experimentation
Cristina Cornelio, Lucrezia Furian, Antonio Nicolò and Francesca Rossi
Inferring Work Task Automatability from AI Expert Evidence
Paul Duckworth, Logan Graham and Michael Osborne
Posters for this session will be presented on January 28th at 4pm
January 28th, 3:00 PM – 4:00 PM
Session 9: Human and Machine Interaction
Chair: Anca Dragan
Robots Can Be More Than Black And White: Examining Racial Bias Towards Robots
Arifah Addison, Kumar Yogeeswaran and Christoph Bartneck
Tact in Noncompliance: The Need for Pragmatically Apt Responses to Unethical Commands
Ryan Blake Jackson, Ruchen Wen and Tom Williams
AI Extenders: The Ethical and Societal Implications of Humans Cognitively Extended by AI*
Karina Vold and Jose Hernandez-Orallo
Human Trust Measurement Using an Immersive Virtual Reality Autonomous Vehicle Simulator
Shervin Shahrdar, Corey Park and Mehrdad Nojoumian
Posters for this session will be presented on January 28th at 4pm
* Papers without poster presentation
Arifah Addison, Kumar Yogeeswaran and Christoph Bartneck
Tact in Noncompliance: The Need for Pragmatically Apt Responses to Unethical Commands
Ryan Blake Jackson, Ruchen Wen and Tom Williams
AI Extenders: The Ethical and Societal Implications of Humans Cognitively Extended by AI*
Karina Vold and Jose Hernandez-Orallo
Human Trust Measurement Using an Immersive Virtual Reality Autonomous Vehicle Simulator
Shervin Shahrdar, Corey Park and Mehrdad Nojoumian
Posters for this session will be presented on January 28th at 4pm
* Papers without poster presentation