Causethical ML - Seminar Isabel Valera

News

30.11.2021

Checklist for next abstract submission

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... Read more

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 smiley

 

25.11.2021

Reminder: Please upload your presentations in CMS and send us an email, if we can share it

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... Read more

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

24.11.2021

Today Explainability Panel - Questions/points to be discussed

Dear all,

Today, you will be participating in the causal explainability block panel. For your reference, we will be discussing the following questions/points, time permitting:

  • What major highlights can we take from each paper presentation?
  • Are the methods... Read more

Dear all,

Today, you will be participating in the causal explainability block panel. For your reference, we will be discussing the following questions/points, time permitting:

  • What major highlights can we take from each paper presentation?
  • Are the methods discussed trying to explain the model or just the data?
  • The causal interpretations are made on a non-causal black-box model, which means that the best they can do is to investigate the model - rather than the actual causal mechanism.
  • When we have the choice which approach to apply, how do we select an appropriate explanation model?
  • And how can we compare the results of different explanation models when applied to the same underlying ML model and input data?
  • Should we concentrate on methods of acquiring experimental data for explaining causal relationships in machine learning or continue to explore different approaches limited to the minimal assumptions mentioned in these papers?

 

Best wishes,
Your CausethicalML Team

17.11.2021

Template in materials section

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... Read more

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

10.11.2021

Submission of abstracts & presentations

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,... Read more

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

 

 

05.11.2021

FAQ Presentation & Abstract + Deadlines

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... Read more

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

Show all
 

 

Causethical ML - Seminar

Welcome to the Causethical Machine Learning (ML) Seminar this winter semester 2021/22! We are excited for fruitful discussions on recent advances and potential future developments of cauality, ethics and machine learning. Please find information about the schedule of the course and all paper we will read on our website.

This CMS will be the place where...

  • we communicate news to you.
  • we may upload course material beyond the papers on the website.
  • you may upload your assignments and materials.

If you have questions, send us causethical-ml [at] lists.saarland-informatics-campus.de.

About the seminar

Causality and ethical ML are two mostly disjoint fields in machine learning. Recently, their intersection is attracting increasing attention as models are deployed for consequential decision-making domains. However, most existing literature only sporadically explores this intersection. The aim of this seminar is to bring these efforts together to open a channel of discussion and potential investigations to fill the gaps. Specifically, the seminar focuses on investigating progress in the fields of fairness, explainability and robustness in ML through a causal lens.

 

Deliverables

Every enrolled student will need to give a talk about the selected paper, participate in at least one discussion panel, and deliver 3 single-page summaries corresponding to the 3 blocks covered in the course.

 

Date & Place

The seminar will take place weekly on Wednesdays from 16:15-17:45 an online manner (via Zoom). Attendance to weekly meetings is mandatory.

First lecture will take place on October 27th. The first two lectures will provide an overview of causality and will be open to all seminar applicants.

 

Visiting students

Due to the overwhelming interest in the seminar, we are unfortunately unable to offer every student a place in the seminar. If you are interested in attending the seminar as a visiting student (i.e. we will be unable to give you credits and cannot offer you to present in class), send us an email to causethical-ml [at] lists.saarland-informatics-campus.de

 

 



Privacy Policy | Legal Notice
If you encounter technical problems, please contact the administrators