Seminar on Explainable Artificial Intelligence (FSS 2022)

With the superior results achieved by black box machine learning techniques, in particular neural networks, there has been an increasing demand for understanding how an artificial intelligence (AI) system achieves its results and decisions. This sparked the field of explainable artificial intelligence (also coined explainable AI or XAI).

Goals

In this seminar, you will familiarize yourself with recent advancements in the field of explainable artificial intelligence. You will read research papers as well as conduct own experiments where applicable, and you will discuss the insights with the other participants of the seminar.

As a participant, you are supposed to introduce a particular XAI technique and present it to the seminar participants. Each seminar paper undergoes a peer review process in the seminar. Presentations are supposed to be about 25 minutes long.

Organization

This seminar is organized by Prof. Dr. Heiko Paulheim

Available for Master students (2 SWS, 4 ECTS)

Prerequisites: none

Additional resources:

LaTeX template

Schedule

For now, we plan with an on-campus seminar.

February 24th, 13:45–15:15: kick off meeting: B6 23-25, A302 Slides
March 1st: topic assignment
March 30th: paper draft due
April 14th: peer review due
April 28th, May 5th, 12th, 19th: 13:45–17:00 presentations and discussions (see schedule below), B6 23-25, A303
June 18th: final paper due

Registration
Registration will be available in Portal2
Note that we are planning to conduct this seminar as an in person event, so that you should only select it if you are planning to be in Mannheim in the spring term
After the kick off session, please send a ranked list of three topics you would like to read and present in the seminar to Bianca Lermer
Final assignment of topics will be made after the kick off meeting
Presentation Schedule
There will be four dates with 2–3 presentations each:
28.4.: (1) Surrogate Models, (2) Model Distillation, (3) Local interpretable model-agnostic explanations (LIME)
5.5.: (1) Rule Extraction from Neural Networks, (2) Layer-wise Relevance Propagation
12.5.: (1) Feature Importance, (2) Shapely Values
19.5.: (1) Saliency Maps, (2) Counterfactual Explanations, (3) Prototypes and Criticisms

Note: the topic list below does contains one literature pointer per topic. These papers are examples, but they are not exhaustive, i.e., it is part of your task to collect more papers on the topic.

Topic	Example Paper
Local interpretable model-agnostic explanations (LIME)	Ribeiro et al.: “Why Should I Trust You?”: Explaining the Predictions of Any Classifier, 2016
Feature importance	Casalicchio et al.: Visualizing the Feature Importance for Black Box Models, 2018
Shapeley values	Lindberg and Lee: A Unified Approach to Interpreting Model Predictions, 2017
Saliency maps	Simonyan et al.: Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, 2013
Activation maximization	Erhan et al.: Understanding Representations Learned in Deep Architectures, 2010
Surrogate models	Bastani et al.: Interpretability via Model Extraction, 2017
Rule extraction	Zilke et al.: DeepRED – rule extraction from deep neural networks, 2015
Partial dependence plots (PDP)	Cafri and Bailey: Understanding Variable Effects from Black Box Prediction: Quantifying Effects in Tree Ensembles Using Partial Dependence, 2021
Individual conditional expectation	Goldstein et al.: Peeking Inside the Black Box: Visualizing Statistical Learning With Plots of Individual Conditional Expectation, 2015
Decomposition	Robnik-Šikonja et al.: Explaining Classifications For Individual Instances, 2008
Model distillation	Tan et al.: Distill-and-Compare: Auditing Black-Box Models Using Transparent Model Distillation, 2017
Sensitivity analysis	Cortez and Embrechts: Using sensitivity analysis and visualization techniques to open black box data mining models, 2013
Layer wise relevance propagation (LRP)	Montavon et al.: Layer-Wise Relevance Propagation: An Overview, 2019
Prototypes and criticisms	Kim et al.: Examples are not Enough, Learn to Criticize! Criticism for Interpretability, 2016
Counterfactual explanations	Wachter et al.: Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR, 2017

Recommended Reading
The following articles provide introductions and surveys for the topic and are recommended for all seminar participants to read:
Amina Adadi and Mohammed Berrada: Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI), 2018
Plamen P. Angelov et al.: Explainable artificial intelligence: an analytical review, 2021
Vanessa Buhrmester et al.: Analysis of explainers of black box deep neural networks for computer vision: A survey, 2021
Miruna A. Clinciu and Helen F. Hastie: A Survey of Explainable AI Terminology, 2019
Roberto Confalonieri et al.: A historical perspective of explainable Artificial Intelligence, 2020
Derek Doran et al.: What Does Explainable AI Really Mean? A New Conceptualization of Perspectives, 2017
Doshi-Velez and Kim: Towards a Rigorous Science of Interpretable Machine Learning, 2017
Randy Goebel et al.: Explainable AI: The New 42?, 2018
Zachary C. Lipton: The Mythos of Model Interpretability, 2016
Gabriëlle Ras et al.: Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges, 2018

Seminar on Explainable Artificial Intelligence (FSS 2022)

Goals

Organization

Schedule

Registration

Presentation Schedule

Topics

Recommended Reading

Data and Web Science Group