( events)   Timezone: »  
Mon Dec 13 01:00 AM -- 12:30 PM (PST)
Algorithmic Fairness through the lens of Causality and Robustness
Jessica Schrouff · Awa Dieng · Golnoosh Farnadi · Kweku Kwegyir-Aggrey · Miriam Rateike

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?

Opening remarks (opening remarks by organizers)
Speaker Intro (live intro)
Invited Talk: Generalizability, robustness and fairness in machine learning risk prediction models (Invited Talk)
Q&A for Rumi Chunara (live questions)
Short break (short break)
Speaker Intro (live intro)
Invited Talk: Path-specific effects and ML fairness (live talk)
Q&A for Silvia Chiappa (live questions)
Short break (short break)
Speaker Intro (live intro)
Invited Talk: Causality and fairness in ML: promises, challenges & open questions (live talk)
Q&A for Isabel Valera (live questions)
Intro to Contributed Talks (live intro)
Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation (Oral)
On the Impossibility of Fairness-Aware Learning from Corrupted Data (Oral)
Achieving Counterfactual Fairness for Causal Bandit (Oral)
Q&A for Contributed talks 1,2,3 (live questions)
Poster session 1 (Poster session: join us on gathertown)
Intro to Roundtables (live intro)
Roundtables (Roundtable discussions: join us on gathertown)
Short break (Short break: join us on gather.town)
Fairness for Robust Learning to Rank (Poster)
Cooperative Multi-Agent Fairness and Equivariant Policies (Poster)
Fair SA: Sensitivity Analysis for Fairness in Face Recognition (Poster)
Measure Twice, Cut Once: Quantifying Bias and Fairness in Deep Networks (Poster)
Bounded Fairness Transferability subject to Distribution Shift (Poster)
Counterfactual Fairness in Mortgage Lending via Matching and Randomization (Poster)
Structural Interventions on Automated Decision Making Systems (Poster)
Balancing Robustness and Fairness via Partial Invariance (Poster)
Implications of Modeled Beliefs for Algorithmic Fairness in Machine Learning (Poster)
Fairness Degrading Adversarial Attacks Against Clustering Algorithms (Poster)
Long break (Long break: join us on gather.town)
Intro to Afternoon session (live intro)
Speaker Intro (live intro)
Invited Talk: Causality and Fairness (live talk)
Q&A for Elias Bareinboim (live questions)
Speaker Intro (live intro)
Invited Talk: Towards Reliable and Robust Model Explanations (Invited talk)
Q&A for Hima Lakkaraju (live questions)
Intro to Contributed Talks (live intro)
The Many Roles that Causal Reasoning Plays in Reasoning about Fairness in Machine Learning (Oral)
Detecting Bias in the Presence of Spatial Autocorrelation (Oral)
Fair Clustering Using Antidote Data (Oral)
Q&A for Contributed talks 4,5,6 (live questions)
Short Break (short break)
Speaker Intro (live intro)
Invited Talk: Lessons from robust machine learning (live talk)
Q&A for Aditi Raghunathan (live questions)
Short break (short break)
Panel: Been Kim (Google Brain), Solon Barocas (Microsoft Research), Ricardo Silva (UCL), Rich Zemel (U. of Toronto) (Live Discussion)
Poster session 2 (Poster session: join us on gathertown)
Closing remarks (Closing remarks by organizers)