Causethical Machine Learning

Dear Students, 

Your final grades for the seminar are now available.
You can view both your grade and the total points in your personal status.

We have also uploaded the detailed feedback on your final reports. Please take a look, and don’t hesitate to reach out if you have any questions or would like further clarification.

It was a pleasure having you in the seminar, we hope you not only enjoyed it but also learned a lot from this seminar.

Wishing you all the very best for the upcoming semester!

Thank you. 

Best, 
Causethical ML Team 

Dear all,

This is a gentle reminder that the report submission deadline is Monday, August 4, 2025 EOD. 

Please ensure that your report is submitted via CMS. Email submissions will not be accepted.

Report Guidelines: Your report should be submitted as a PDF. 

• Length: 10 pages (excluding references)

• References: You may include as many pages of references as necessary.

• Style: We encourage you to think creatively, express bold ideas, and share your vision for the future of the field.

Thank you.

All the best,
The Causethical Team

Dear Students,

This is a reminder that the last session of the Causethical Machine Learning Seminar will take place on Tuesday, 15/07/2025.

The final session will be held in the form of a Panel Discussion, and your participation is essential. Please submit your questions in advance via the provided form. Submitting your questions is not only helpful for the discussion but also helps with the evaluation.

Additionally, please remember that the deadline for the final report is Sunday, 4th August. Make sure to plan accordingly and submit your work on time.

Best regards,
Causethical ML Team

 

Dear Students, 
Coming Tuesday (20th May, 2025) we have a guest lecture from Dr. Ruta Binkyte. 

Title : A Causal Perspective on Balancing Competing Goals in Trustworthy Machine Learning

Abstract: As machine learning systems are deployed in increasingly sensitive and high-stakes environments, ensuring their trustworthiness is no longer
optional—it’s imperative. However, core pillars of trustworthy ML—fairness, privacy, robustness, accuracy, and
explainability—often come into conflict when addressed in isolation. This talk explores how causal reasoning provides a powerful framework
to understand and navigate these trade-offs, with a special focus on the challenge of achieving fairness without compromising other goals.

Building on insights from the paper _“Causality Is Key to Understand and Balance Multiple Goals in Trustworthy ML and Foundation
Models”_, we delve into practical examples where causal approaches have enabled more equitable outcomes while preserving performance and
interpretability. We’ll discuss how causal graphs, counterfactual reasoning, and intervention-based analysis can expose hidden biases
and offer actionable pathways toward fairer algorithms. The talk also addresses the limitations and open questions in operationalizing
causality at scale, especially in the context of large foundation models.

We hope to see everyone in the session next week. 

Best, 
Causethical ML Team

Dear Students, 

You can now view your assigned presentation blocks.
Please review the schedule carefully and ensure that you are attending your sessions in person, including any panel discussions you are part of.

Details of your assigned papers will be shared with you shortly.

Thank you!

Best, 
Causethical ML Team

Dear Students, 
Welcome to Causethical ML 2.0 Seminar. 

As you might have noticed, the seminar is divided into 3 major themes/blocks.
As a first step to know you better and assign you better during the seminar, please select the preferences for the block you are interested in:
a) Block 1: Fairness and Causality
b) Block 2: Robustness and Causality
c) Block 3: Interpretability and Causality

For doing so, go to your personal status and under "tutorial preferences" and select your preference and click save.
Please don't use "Not possible" as a preference. 

Please do this by 21st April, 2025. 

Thank you. 

Best, 
Causethical ML Team