Lecture notes for 'Interpretable Machine Learning' at UoW. Summer semester 2020/2021
Slack for this course: http://iml2021workspace.slack.com
XAI stories ebook (last year): https://github.com/pbiecek/xai_stories
eBook: https://github.com/pbiecek/xai_stories_2
The course consists of lectures, computer labs and a project.
The course is elective. The rules of passing may seem non-standard. Make sure that you understand them to avoid unpleasant consequences. I believe that one of the most important skills in building ML/XAI models is flexibility and a proactive approach to the problem. In this course, the assessment criteria will strongly reward both flexibility and a proactive approach.
The design of this course is based on four principles:
- Mixing experiences during studies is good. It allows you to generate more ideas. Also, in mixed groups, we can improve our communication skills,
- In XAI, the interface/esthetic of the solution is important. XAI, like earlier HCI (Human Computer Interaction), is on the borderline between technical, domain and cognitive aspects. Therefore, apart from the purely technical descriptions, the results must be grounded in the domain and are communicated aesthetically and legibly,
- communication of results is important. Both in science and business, it is very important to be able to present the results concisely and legibly. In this course, it should translate into the ability to describe one XAI story in the form of a short chapter/article.
- It is worth doing useful things. Let's look for new applications for XAI methods discussed on typical predictive problems.
Plan for the summer semester 2020/2021. UoW classes are on Fridays. We will meet online here: meet.google.com/yfq-hckf-pgu.
- 2021-03-05 -- Introduction
- 2021-03-12 -- 14:00 [XAI stories: first meeting, groups are assembled]
- 2021-03-19 -- Break Down / SHAP. EMA chapter, paper shap, paper break down
- 2021-03-26 -- LIME. EMA chapter, paper lime
- 2021-03-31 -- Ceteris Paribus profiles / Partial Dependence profiles. EMA chapter, paper pdp/ale
- 2021-04-09 -- 14:00 [XAI stories: first version of the solution]
- 2021-04-16 -- Variable's importance. EMA chapter, paper pvi
- 2021-04-23 -- Interactive Explanatory Model Analysis - how instance level methods complement each other
- 2021-04-30 -- Fairness or Model diagnostic plots. EMA chapter, paper auditor
- 2021-05-14 -- 14:00 [XAI stories: second version of the solution]
- 2021-05-21 -- students presentations
- 2021-05-28 -- students presentations
- 2021-06-04 -- 14:00 [XAI stories: final presentations] (!! USOS says 11)
From different activities, you can get from 0 to 100 points. 51 points are needed to pass this course.
Grades:
- 51-60: dst
- 61-70: dst+
- 71-80: db
- 81-90: db+
- 91-100: bdb
There are three key components.
Chapter in the 'XAI stories' [0-60 points]
- quality of trained predictive models [0-10 points]
- quality of dataset level explanations [0-10 points]
- quality of instance level explanations [0-10 points]
- quality of the charts/visuals/diagrams [0-10 points]
- the relevance of the example [0-10 points]
- presentation of key results during the final meeting [0-10 points]
Presentation of a selected XAI related article [0-10 points]
Home works [0-30 points]
- home work 1 for 0-5 points: Train a predictive model for selected ML problem (see issues). Submit knitr/notebook script to GitHub (directory Homeworks/H1/FirstnameLastname). Deadline: 2020-03-11 EOD
- [home work 2] for 0-5 points. Deadline: 2021-03-26 EOD
- [home work 3] for 0-5 points. Deadline: 2020-04-09 EOD
- [home work 4] for 0-5 points. Deadline: 2020-04-16 EOD
- [home work 5] for 0-5 points. Deadline: 2020-05-07 EOD
- [home work 6] for 0-5 points. Deadline: 2020-05-21 EOD
Presentations can be prepared by one or two students. Each group should present a single XAI related paper (journal or conference). Each group should choose a different paper. Here are some suggestions.
- Revealing the Dark Secrets of BERT note, that you need to have some knowledge related to NLP to take this topic,
- Explanation in Artificial Intelligence: Insights from the Social Sciences by Tim Miller
- Explainable AI for Trees: From Local Explanations to Global Understanding by Scott Lundberg
- One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques by Vijay Arya et al
- iNNvestigate neural networks by Maximilian Alber et al
- Veridical Data Science by Bin Yu at NIPS19
- Agency + Automation: Designing Artificial Intelligence into Interactive Systems Jeff Heer by Jeff Heer at NIPS19
- other papers from this list https://github.com/pbiecek/xai_resources
- Soft: https://captum.ai/
Project proposals are described as issues in this repository. Each issue is a single problem in which you need to train a few predictive models and explain them. Among different issues, you will fond applications in different areas, some concern medical data, some concern financial data.
Each group of students should choose one issue they want to solve. After consultation with the lecturer, you can also submit your projects. Projects should be solved in groups. The ideal group consists of three people, one student from each university. Data Scientists from McKinsey will help us with these projects. More details about the rules of cooperation will be given during classes.
The project ends with a small article prepared in English and a short presentation summarizing the key results. The study will be available to the public in the form of open-gitbook.
See Limitations of Interpretable Machine Learning Methods as an example to follow. During this course, we are going to gather several use-cases/success stories for explainable machine learning.
The literature will be added on an ongoing basis.