Masterarbeit - Machine Learning: Concept Extraction Validation Benchmark

Fraunhofer-Gesellschaft; Stuttgart; Vor Ort; EUR 60.000 - 80.000; Vollzeit

Zusammenfassung

A leading research institute in Germany is looking for candidates to conduct a thesis on concept-based Explainable Artificial Intelligence (XAI) methods. The role involves literature review, developing evaluation metrics, and empirical testing of XAI methods. Proficiency in Python and a solid understanding of machine learning are essential. The position offers a collaborative research environment with University of Stuttgart and RWTH Aachen University.

Qualifikationen

• Solid understanding of machine learning concepts.
• Strong programming skills in Python.
• Ideally, prior experience with explainability or XAI methods.

Aufgaben

• Conduct a literature review on trustworthy explanations.
• Select or develop evaluation metrics for concept-based XAI methods.
• Empirical benchmarking of a concept extraction method.

Kenntnisse

Proficiency in Python

Understanding of machine learning

Good English communication skills

Tools

Modern ML libraries

Jobbeschreibung

Field of study: computer science, mathematics, software design, software engineering, technical computer scienceor comparable.

Machine Learning (ML) models are reaching a maturity level that allows their operational use in businesses. However, in some areas, this use is limited by their ”black box” nature: the decision-making logic and potential errors of a model are not transparent, making it unsuitable for safety-critical applications or those requiring trust in the model. The field of Explainable Artificial Intelligence (XAI) addresses this by providing methods to make model behavior more interpretable. Among these, concept-based and prototype-based methods show promise in offering intuitive insights into model decisions. To truly build trust and ensure safe deployment of models, however, it is not enough for XAI methods to be intuitive — they must must also meet some key requirements. For example, the methods need to be reliable and their explanations need to be faithful to the model, while having a complexity level appropriate for human users. To ensure that these properties are met, XAI methods must be rigorously validated. Furthermore, such an evaluation should be systematic, allowing to compare most methods on the same ground. A framework for this is still largely missing in current XAI pipelines.

This thesis investigates the systematic benchmarking of concept-based explanation methods formachine learning models. It adapts an existing benchmarking framework, originally developed for pro-totype methods, to support the evaluation of concept-based explanations. The project also includes theempirical testing of concept extraction methods, evaluating their effectiveness and reliability using diverse metrics and datasets. The work contributes toward standardizing the evaluation of XAI techniquesto ensure that generated explanations are meaningful and faithful to the underlying model.

What you will do

The candidate will first conduct a literature review to identify desirable properties of trustworthy explanations and corresponding evaluation criteria. This includes analyzing existing benchmarks, theoreticalfoundations, and practical requirements of concept-based XAI methods. Based on this, suitable evaluation metrics will be selected or developed and integrated into the benchmarking pipeline. The newlyimplemented metrics will then be used to evaluate a concept extraction method in various scenarios.

This requires proficiency in Python and familiarity with modern ML libraries.

Scope:

• Identifying and formalizing evaluation properties for concept-based XAI methods
• Adapting an existing benchmark suite for prototype methods to accommodate concept-based explanations
• Implementing and testing relevant evaluation metrics
• Empirical benchmarking of a selected concept extraction method across multiple datasets and
  models

What you bring to the table

• Solid understanding of machine learning
• Strong programming skills in Python
• Ideally, prior experience with explainability or XAI methods
• Independent, reliable, and result-oriented working style
• Good English communication skills

What you can expect

• Interesting tasks in applied research
• Intensive support during the project
• Collaboration projekt with University of Stuttgart IFF and RWTH Aachen University DSME

We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability.

With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process. As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.

Interested? Apply online now. We look forward to getting to know you!

Ms. Lisa Bauer
Recruiting
Tel. [phone]

[e-mail]

Fraunhofer Institute for Manufacturing Engineering and Automation IPA

www.ipa.fraunhofer.de

Requisition Number: 79958