Causethical ML - Seminar

Dear students,

You can now find your final grades for the Causethical seminar in CMS. They are displayed as "Points", but refer to your grade in the German grading scale. That is, 1.0 is the best grade and passing grade is 4.0. In case you have any questions regarding your grade please send us an email before 28th Feb (next Monday).

Cheers,

Causethical team

 

 

 

 

Dear all,

Tomorrow, we will have the last presentation of the robustness block followed by the panel session. For your reference, we will be discussing some of the following questions/points.

 

Questions about concepts related to robustness

• What is the difference between generalization and OOD generalization? What type of generalization do the models studied aim to achieve
• What is the difference between the tasks of domain adaptation and unsupervised domain adaptation? Which paper refers to which task?
• Is the meaning of "Invariant features" and "causal features" the same? What are the similarities and differences? Follow-up question: are all invariant features causal or vice versa?

 

Questions about the studied papers

• Why does IRM method fail? Is it due to the assumptions? is it the optimization? Are we modeling direct causes of actions or just invariant features?
• What type of prior knowledge is required in the IRM approaches? Do we need any causal knowledge at all, e.g. causal graph?
• How does the method proposed in the paper "Domain Adaptation by using..." relates/differs from IRM?
• Although deep CAMA trained on clean MNIST data generalizes better to unseen shifts and shows even improved performance when fine-tuned with shifted test data, it is the most complex model among the ones considered here. Therefore, is questionable whether it can be well-fitted in tasks more complex than MNIST. What are other limitations of CAMA?
• Regarding the last paper: In which way and for what could we use counterfactual statements to improve the approach?
• Regarding the last paper: What are the differences between (construction of) adversarial and real-world causal graphs?
• All the papers have a lot margin for improvement...which one would you choose to extend and why?

 

General robustness questions

• Are causally motivated robust machine learning approaches just a means to estimate the functional information on top of (given) causal structure? Or is there more to them?
• Should we focus on solving robustness problems through formulating vulnerability of models or through modeling perturbations and possible attacks? What are the advantages and drawbacks of each type of approach?
• Given the many non-trivial assumptions made in the various techniques, how can we measure progress in a way that is universally valid for the various techniques?
• Is not lack of robustness related to lack of fairness in algorithms? Both stem from spurious correlations learned. How are they theoretically different? will robust models be explainable and fair?
• Should we aim to develop robust machine learning in any application? Why?

 

General machine learning questions

• Looking at the results, the increase in performance does not seem to be as significant as the author claims. Is such a bold claim normal in research? (If you would like to learn about good academic research practice, I suggest reading https://arxiv.org/pdf/2108.02497.pdf)

 

 

See you tomorrow!

Best wishes,
Your CausethicalML Team

Dear students,

This is just a friendly reminder about the abstract submission for the block of robustness, which is today.  As with previous submissions, this is a short checklist with the information it should include: 

• The abstract should provide an overview of all the papers of the block with main conclusions comparing them and their views
• The abstract should be 1 page long using the template we provide in the materials section. This is 1 page excluding references (i.e., references can be on the next page).
• You should include references, whenever suitable/necessary.
• The abstract should include at least 2 questions that would be suitable to ask at the panel.

 

On a different note, please upload your presentation on CMS. Then, then send us an email (A) confirming that you have uploaded it on CMS and (B) whether you are ok that we upload your presentation under the materials section (visible to all students formally registered in this seminar), such that other's can profit from it. While we encourage you to share it with your peers, your decision will not influence your grading.

If you have any more questions, we are happy to answer them.

Looking forward to the last panel session!

Your Causethical ML Team

Hi all,

Thank you so much for your participation today and the engaging discussion! I personally very much enjoyed that so many of you entered the discussion with their ideas, examples and thoughts.

For those of you interested, I wanted to not leave you without a reference to two of the papers I mentioned today during the session:

• What’s Sex Got to Do With Fair Machine Learning? by Lily Hu & Issa Kohler-Hausmann (FAccT'21)
• Causal multi-level fairness by Vishwali Mhasawade & Rumi Chunara (AIES'21)

Enjoy the break! Keep safe and healthy! Looking forward to seeing you all again next year!

Best,

Miriam

Dear students,

As discussed last time, we would like to give you a short checklist for your next abstract submission:

• The abstract should provide an overview of all the papers of the block with main conclusions comparing them and their views
• The abstract should be 1 page long using the template we provide in the materials section. This is 1 page excluding references (i.e., references can be on the next page).
• You should include references, whenever suitable/necessary.
• The abstract should include at least 2 questions that would be suitable to ask at the panel.

If you have any more questions, we are happy to answer them tomorrow!

Looking forward to seeing you tomorrow,

Your Causethical ML Team

 

Dear all,

This is a friendly reminder for the next steps after you have given a presentation:

1. Please upload your presentation on CMS.

2. Please then send us an email (A) confirming that you have uploaded it on CMS and (B) whether you are ok that we upload your presentation under the materials section (visible to all students formally registered in this seminar), such that other's can profit from it. While we encourage you to share it with your peers, your decision will not influence your grading.

Kindly do these two steps directly the day of your presentation or the next day such that others may potentially profit from going through your slides again - if you agree to share.

Thank you,

Your CausethicalML Team

Hi all,

we have uploaded a LaTeX template to the materials section, which you may use for the abstract. Thank you to Tejumade for kindly sharing it with us.

As for the content, please assure to include, an overview of the papers with man conclusions comparing them, their view and questions.

Best regards,

Your CausethicalML Team

Dear all,

Thank you to the two presenters who kicked-off this semester's seminar today and to the others for engaging in a vivid discussion! To summarize the submission instructions given by Prof. Valera:

1. Presentations

After you presented in class, please upload your presentations on CMS under "My presentation" as a pdf file. Once you submitted it, please send us an email to the causethical-ml email list indicating whether you would like your presentation to be shared with your peers. In this case we will upload it in the material section on CMS and it will only visible to students accepted in this seminar. Otherwise, please indicate that you do not want the presentation to be uploaded and shared with your peers. While we highly encourage you to share your presentation, please note that your decision will not affect grading.

2. Abstracts

Please upload your abstracts in the submission section on CMS. Check out the deadlines in the schedule on our website.

 

If you have any questions, please do not hesitate to reach out to us. Thank you and we look forward to next week!

Best,

Your CausethicalML Team

 

 

Dear students,

Some of you have been wondering about the format of your presentation, and about the technical details you are expected to cover in your presentation from your assigned paper. Allow us to summarize below.

For your 30 min talk, you have two options: i) give general idea, assumptions, intuition and limitations ii) focus on the most interesting technical contribution and explain it, with just a bit of motivation/overview

While many of the papers are complete in the sense that most necessary background knowledge is in the paper, some may require you to know (and hence read) material from elsewhere that is not covered in the paper itself. Should this be the case, use your best judgment: your exposition of the paper should strive to explain (most of) the necessary preliminaries in order for an audience to understand and follow along, and have a concrete take-home message. Remember, you will also be writing a 1-page summary for each block covering the papers therein, your presentation may greatly aid this writing for others and vice versa :wink:. Moreover, don't worry about repeating necessary background information from an earlier talk; having these points of overlap is important for the panel discussion to go smoothly.

Finally, as a reminder, the "panel" will be held in the third lecture of each of the three blocks. Students are expected to hand in their 1-page summary of the papers in the block 2 days before the panel lecture, so on Monday. In total, you will submit 3 summaries, 1 per block, not 1 per week. You may submit via CMS (submission is open).

Please note, the exact schedule can be found https://sites.google.com/view/uds-causethical-ml-seminar/schedule

Let us know, if you have any questions. We are happy to support you!

Best,
Your CausethicalML Team