News
Announcement: One-on-One Meeting ScheduleWritten on 19.11.24 (last change on 19.11.24) by Hanwei Zhang Dear all, Here is the schedule for your upcoming one-on-one meetings. Please make a note of your assigned date and time. Ensure that you are punctual and prepared for the meeting. Monday 25 Nov. 2024 in Building E1 3, Room 523
Tuesday 26… Read more Dear all, Here is the schedule for your upcoming one-on-one meetings. Please make a note of your assigned date and time. Ensure that you are punctual and prepared for the meeting. Monday 25 Nov. 2024 in Building E1 3, Room 523
Tuesday 26 Nov. 2024 in Building E1 3, Room 523
Friday 29 Nov. 2024 in Building E1 3, Room 528
If you have any questions or need to reschedule, please contact me as soon as possible. Thank you! Hanwei |
Office Hours Now Available on the TimetableWritten on 04.11.24 by Hanwei Zhang Dear all, I am pleased to announce that office hours are now accessible on the timetable for your convenience. The first scheduled office hour will be on Wednesday at 15:00 in Building E1 3, Room 523. Additional dates and times will be added soon, so please check the timetable regularly for… Read more Dear all, I am pleased to announce that office hours are now accessible on the timetable for your convenience. The first scheduled office hour will be on Wednesday at 15:00 in Building E1 3, Room 523. Additional dates and times will be added soon, so please check the timetable regularly for updates. Looking forward to meeting with you during these times to assist with any questions or guidance you may need. Best regards, Hanwei |
Announcement: Assignment Topics Confirmed – Thank You for Your Selections!Written on 01.11.24 by Hanwei Zhang Hey all, Thank you all for taking the time to complete the topic bidding process! Your thoughtful selections reflect a strong interest in advancing our understanding of model explainability and interpretability, and we’re excited to see the unique perspectives you’ll bring to these advanced… Read more Hey all, Thank you all for taking the time to complete the topic bidding process! Your thoughtful selections reflect a strong interest in advancing our understanding of model explainability and interpretability, and we’re excited to see the unique perspectives you’ll bring to these advanced topics. Here are your confirmed assignments:
Now that topics are finalized, please start by reviewing the assigned paper, available through the links provided in the slides from our kick-off course. As you investigate the paper and related concepts in explainable AI, gather relevant information to structure your research. Then, begin developing your assignments, focusing on clarity, depth, and originality. Resources & Support Important: Thank you once again for your participation in the topic selection process. I am eager to see the insights and creativity each of you will bring to these exciting areas of machine learning explainability. Best regards, Hanwei |
Exploring Explainability in Machine Learning
Registration:
If you are interested in taking this seminar, please register after 11.09.2024 on the faculty's page for seminar assignments: https://seminars.cs.uni-saarland.de/seminars2425.
Registration directly in the dCMS is not possible. You will receive a token from us to register in dCMS once you have been successfully assigned a slot in this seminar by the system.
Registration in LSF/HISPOS
You must register in LSF/HISPOS no later than 3 weeks after the kick-off event.
Otherwise, we will not be able to record your grades at the end of the semester.
If your degree program does not use LSF/HISPOS, you will receive an old-fashioned paper certificate to present to your examination office.
Please contact us early regarding this.
Overview
This seminar course delves into the crucial and evolving field of explainability in machine learning (ML). As ML models become increasingly complex and integral to various domains, understanding how these models make decisions is essential. This course will explore different methodologies for interpreting ML models, including rule-based, attribution-based, example-based, prototype-based, hidden semantics-based, and counterfactual-based approaches. Through a combination of paper readings, discussions, and presentations, students will gain a comprehensive understanding of the challenges and advancements in making ML models transparent and interpretable.
Requirements:
- The student should take a course in machine learning or have sufficient knowledge from other courses;
- The student should speak English and understand that the seminar will be conducted entirely in English.
Places: 8
Schedule
(Could be changed)
| Week | Start | Stop | Date | Event |
| 1 | 21.10.24 | 25.10.24 |
23.10.24 16:00 - 18:00 E1 3, Room 528 |
Kickoff + Tutorial |
| 2 | 28.10.24 | 01.11.24 | Bid + Assign | |
| 3 | 04.11.24 | 08.11.24 | Read | |
| 4 | 11.11.24 | 15.11.24 | Read | |
| 5 | 18.11.24 | 22.11.24 | Prepare Story | |
| 6 | 25.11.24 | 29.11.24 | Meet | |
| 7 | 02.12.24 | 06.12.24 | Prepare Slides | |
| 8 | 09.12.24 | 13.12.24 | Prepare Slides | |
| 9 | 16.12.24 | 20.12.24 | Presentation 1&2 | |
| - | Christmas Break | |||
| - | Christmas Break | |||
| 10 | 06.01.25 | 10.01.25 | Presentation 3&4 | |
| 11 | 13.01.25 | 17.01.25 | Presentation 5&6 | |
| 12 | 20.01.25 | 24.01.25 | Presentation 7&8 | |
| 13 | 27.01.25 | 31.01.25 | Retrospective |
Submission Deadlines:
Report: Feb. 15
Review Opinion: Feb. 28
Revised Report: Mar. 15