Workshop
Algorithmic Fairness through the lens of Causality and Robustness
Jessica Schrouff · Awa Dieng · Golnoosh Farnadi · Mark Kwegyir-Aggrey · Miriam Rateike
Mon 13 Dec, 1 a.m. PST
Trustworthy machine learning (ML) encompasses multiple fields of research, including (but not limited to) robustness, algorithmic fairness, interpretability and privacy. Recently, relationships between techniques and metrics used across different fields of trustworthy ML have emerged, leading to interesting work at the intersection of algorithmic fairness, robustness, and causality.
On one hand, causality has been proposed as a powerful tool to address the limitations of initial statistical definitions of fairness. However, questions have emerged regarding the applicability of such approaches in practice and the suitability of a causal framing for studies of bias and discrimination. On the other hand, the Robustness literature has surfaced promising approaches to improve fairness in ML models. For instance, parallels can be shown between individual fairness and local robustness guarantees. In addition, the interactions between fairness and robustness can help us understand how fairness guarantees hold under distribution shift or adversarial/poisoning attacks.
After a first edition of this workshop that focused on causality and interpretability, we will turn to the intersectionality between algorithmic fairness and recent techniques in causality and robustness. In this context, we will investigate how these different topics relate, but also how they can augment each other to provide better or more suited definitions and mitigation strategies for algorithmic fairness. We are particularly interested in addressing open questions in the field, such as:
- How can causally grounded fairness methods help develop more robust and fair algorithms in practice?
- What is an appropriate causal framing in studies of discrimination?
- How do approaches for adversarial/poisoning attacks target algorithmic fairness?
- How do fairness guarantees hold under distribution shift?
Schedule
Mon 1:00 a.m. - 1:10 a.m.
|
Opening remarks
(
opening remarks by organizers
)
>
SlidesLive Video |
Awa Dieng 🔗 |
Mon 1:10 a.m. - 1:12 a.m.
|
Speaker Intro
(
live intro
)
>
|
🔗 |
Mon 1:12 a.m. - 1:34 a.m.
|
Invited Talk: Generalizability, robustness and fairness in machine learning risk prediction models
(
Invited Talk
)
>
SlidesLive Video |
Rumi Chunara 🔗 |
Mon 1:34 a.m. - 1:45 a.m.
|
Q&A for Rumi Chunara
(
live questions
)
>
|
🔗 |
Mon 1:45 a.m. - 1:50 a.m.
|
Short break
(
short break
)
>
|
🔗 |
Mon 1:50 a.m. - 1:52 a.m.
|
Speaker Intro
(
live intro
)
>
|
🔗 |
Mon 1:52 a.m. - 2:20 a.m.
|
Invited Talk: Path-specific effects and ML fairness
(
live talk
)
>
SlidesLive Video |
Silvia Chiappa 🔗 |
Mon 2:20 a.m. - 2:30 a.m.
|
Q&A for Silvia Chiappa
(
live questions
)
>
|
🔗 |
Mon 2:30 a.m. - 2:40 a.m.
|
Short break
(
short break
)
>
|
🔗 |
Mon 2:40 a.m. - 2:42 a.m.
|
Speaker Intro
(
live intro
)
>
|
🔗 |
Mon 2:42 a.m. - 3:10 a.m.
|
Invited Talk: Causality and fairness in ML: promises, challenges & open questions
(
live talk
)
>
SlidesLive Video |
Isabel Valera 🔗 |
Mon 3:10 a.m. - 3:18 a.m.
|
Q&A for Isabel Valera
(
live questions
)
>
|
🔗 |
Mon 3:18 a.m. - 3:20 a.m.
|
Intro to Contributed Talks
(
live intro
)
>
|
🔗 |
Mon 3:20 a.m. - 3:30 a.m.
|
Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation
(
Oral
)
>
SlidesLive Video |
Agnieszka Słowik · Leon Bottou 🔗 |
Mon 3:30 a.m. - 3:40 a.m.
|
On the Impossibility of Fairness-Aware Learning from Corrupted Data
(
Oral
)
>
SlidesLive Video |
Nikola Konstantinov · Christoph Lampert 🔗 |
Mon 3:40 a.m. - 3:50 a.m.
|
Achieving Counterfactual Fairness for Causal Bandit
(
Oral
)
>
SlidesLive Video |
Wen Huang · Lu Zhang · Xintao Wu 🔗 |
Mon 3:50 a.m. - 4:00 a.m.
|
Q&A for Contributed talks 1,2,3
(
live questions
)
>
SlidesLive Video |
🔗 |
Mon 4:00 a.m. - 5:00 a.m.
|
Poster session 1 ( Poster session: join us on gathertown ) > link | 🔗 |
Mon 5:00 a.m. - 5:05 a.m.
|
Intro to Roundtables
(
live intro
)
>
|
🔗 |
Mon 5:05 a.m. - 6:00 a.m.
|
Roundtables ( Roundtable discussions: join us on gathertown ) > link | 🔗 |
Mon 6:00 a.m. - 6:10 a.m.
|
Short break ( Short break: join us on gather.town ) > link | 🔗 |
Mon 6:10 a.m. - 6:13 a.m.
|
Fairness for Robust Learning to Rank
(
Poster
)
>
SlidesLive Video |
Omid Memarrast · Ashkan Rezaei · Rizal Fathony · Brian Ziebart 🔗 |
Mon 6:13 a.m. - 6:16 a.m.
|
Cooperative Multi-Agent Fairness and Equivariant Policies
(
Poster
)
>
SlidesLive Video |
Niko Grupen · Bart Selman · Daniel Lee 🔗 |
Mon 6:16 a.m. - 6:19 a.m.
|
Fair SA: Sensitivity Analysis for Fairness in Face Recognition
(
Poster
)
>
SlidesLive Video |
Aparna Joshi · Xavier Suau Cuadros · Nivedha Sivakumar · Luca Zappella · Nicholas Apostoloff 🔗 |
Mon 6:19 a.m. - 6:22 a.m.
|
Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Networks
(
Poster
)
>
SlidesLive Video |
Ziliang Zong · Cody Blakeney · Gentry Atkinson · Nathaniel Huish · · Vangelis Metsis 🔗 |
Mon 6:22 a.m. - 6:25 a.m.
|
Bounded Fairness Transferability subject to Distribution Shift
(
Poster
)
>
SlidesLive Video |
Reilly Raab · Yatong Chen · Yang Liu 🔗 |
Mon 6:25 a.m. - 6:28 a.m.
|
Counterfactual Fairness in Mortgage Lending via Matching and Randomization
(
Poster
)
>
SlidesLive Video |
Sama Ghoba · Nathan Colaner 🔗 |
Mon 6:28 a.m. - 6:31 a.m.
|
Structural Interventions on Automated Decision Making Systems
(
Poster
)
>
SlidesLive Video |
efren cruz · Sarah Rajtmajer · Debashis Ghosh 🔗 |
Mon 6:31 a.m. - 6:34 a.m.
|
Balancing Robustness and Fairness via Partial Invariance
(
Poster
)
>
SlidesLive Video |
Moulik Choraria · Ibtihal Ferwana · Ankur Mani · Lav Varshney 🔗 |
Mon 6:34 a.m. - 6:37 a.m.
|
Implications of Modeled Beliefs for Algorithmic Fairness in Machine Learning
(
Poster
)
>
SlidesLive Video |
Ruth Urner · Jeff Edmonds · Karan Singh 🔗 |
Mon 6:37 a.m. - 6:40 a.m.
|
Fairness Degrading Adversarial Attacks Against Clustering Algorithms
(
Poster
)
>
SlidesLive Video |
Anshuman Chhabra · Adish Singla · Prasant Mohapatra 🔗 |
Mon 6:40 a.m. - 7:55 a.m.
|
Long break ( Long break: join us on gather.town ) > link | 🔗 |
Mon 7:55 a.m. - 8:00 a.m.
|
Intro to Afternoon session
(
live intro
)
>
|
🔗 |
Mon 8:00 a.m. - 8:02 a.m.
|
Speaker Intro
(
live intro
)
>
|
🔗 |
Mon 8:02 a.m. - 8:30 a.m.
|
Invited Talk: Causality and Fairness
(
live talk
)
>
SlidesLive Video |
Elias Bareinboim 🔗 |
Mon 8:30 a.m. - 8:40 a.m.
|
Q&A for Elias Bareinboim
(
live questions
)
>
|
🔗 |
Mon 8:40 a.m. - 8:42 a.m.
|
Speaker Intro
(
live intro
)
>
|
🔗 |
Mon 8:42 a.m. - 9:20 a.m.
|
Invited Talk: Towards Reliable and Robust Model Explanations
(
Invited talk
)
>
SlidesLive Video |
Himabindu Lakkaraju 🔗 |
Mon 9:20 a.m. - 9:28 a.m.
|
Q&A for Hima Lakkaraju
(
live questions
)
>
|
🔗 |
Mon 9:28 a.m. - 9:30 a.m.
|
Intro to Contributed Talks
(
live intro
)
>
|
🔗 |
Mon 9:30 a.m. - 9:40 a.m.
|
The Many Roles that Causal Reasoning Plays in Reasoning about Fairness in Machine Learning
(
Oral
)
>
SlidesLive Video |
Irene Y Chen · Hal Daumé III · Solon Barocas 🔗 |
Mon 9:40 a.m. - 9:50 a.m.
|
Detecting Bias in the Presence of Spatial Autocorrelation
(
Oral
)
>
SlidesLive Video |
Subhabrata Majumdar · Cheryl Flynn · Ritwik Mitra 🔗 |
Mon 9:50 a.m. - 10:00 a.m.
|
Fair Clustering Using Antidote Data
(
Oral
)
>
SlidesLive Video |
Anshuman Chhabra · Adish Singla · Prasant Mohapatra 🔗 |
Mon 10:00 a.m. - 10:10 a.m.
|
Q&A for Contributed talks 4,5,6
(
live questions
)
>
SlidesLive Video |
🔗 |
Mon 10:10 a.m. - 10:15 a.m.
|
Short Break
(
short break
)
>
|
🔗 |
Mon 10:15 a.m. - 10:17 a.m.
|
Speaker Intro
(
live intro
)
>
|
🔗 |
Mon 10:17 a.m. - 10:47 a.m.
|
Invited Talk: Lessons from robust machine learning
(
live talk
)
>
SlidesLive Video |
Aditi Raghunathan 🔗 |
Mon 10:47 a.m. - 10:55 a.m.
|
Q&A for Aditi Raghunathan
(
live questions
)
>
|
🔗 |
Mon 10:55 a.m. - 11:00 a.m.
|
Short break
(
short break
)
>
|
🔗 |
Mon 11:00 a.m. - 11:40 a.m.
|
Panel: Been Kim (Google Brain), Solon Barocas (Microsoft Research), Ricardo Silva (UCL), Rich Zemel (U. of Toronto)
(
Live Discussion
)
>
SlidesLive Video |
🔗 |
Mon 11:40 a.m. - 12:20 p.m.
|
Poster session 2 ( Poster session: join us on gathertown ) > link | 🔗 |
Mon 12:20 p.m. - 12:30 p.m.
|
Closing remarks
(
Closing remarks by organizers
)
>
SlidesLive Video |
Miriam Rateike 🔗 |