publications | Berkant Turan

Interpretability Guarantees with Merlin-Arthur Classifiers

Stephan Wäldchen, Kartikey Sharma, Berkant Turan, Max Zimmer, and 1 more author

In Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (AISTATS), PMLR, 2024

Abs Bib PDF Code

We propose an interactive multi-agent classifier that provides provable interpretability guarantees even for complex agents such as neural networks. These guarantees consist of lower bounds on the mutual information between selected features and the classification decision. Our results are inspired by the Merlin-Arthur protocol from Interactive Proof Systems and express these bounds in terms of measurable metrics such as soundness and completeness. Compared to existing interactive setups, we rely neither on optimal agents nor on the assumption that features are distributed independently. Instead, we use the relative strength of the agents as well as the new concept of Asymmetric Feature Correlation which captures the precise kind of correlations that make interpretability guarantees difficult. We evaluate our results on two small-scale datasets where high mutual information can be verified explicitly.
@inproceedings{pmlr-v238-waldchen24a, title = { Interpretability Guarantees with {M}erlin-{A}rthur Classifiers }, author = {W\"{a}ldchen, Stephan and Sharma, Kartikey and Turan, Berkant and Zimmer, Max and Pokutta, Sebastian}, booktitle = {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (AISTATS)}, pages = {1963--1971}, year = {PMLR, 2024}, editor = {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen}, volume = {238}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, }

Extending Merlin-Arthur Classifiers for Improved Interpretability

Berkant Turan

In Joint Proceedings of the xAI-2023 Late-breaking Work, Demos and Doctoral Consortium, co-located with the 1st World Conference on eXplainable Artificial Intelligence (xAI-2023), Jul 2023

6-page extended abstract. Awarded Best Doctoral Proposal at xAI-2023.

Bib PDF

@inproceedings{TuranConsortium2023,
  title = {Extending Merlin-Arthur Classifiers for Improved Interpretability},
  author = {Turan, Berkant},
  booktitle = {Joint Proceedings of the xAI-2023 Late-breaking Work, Demos and Doctoral Consortium, co-located with the 1st World Conference on eXplainable Artificial Intelligence (xAI-2023)},
  pages = {193-200},
  year = {2023},
  organization = {Springer},
  address = {Lisbon, Portugal},
  month = jul,
}

Robustness of Hybrid Discriminative-Generative Models

Berkant Turan

Technical University of Berlin, Jul 2022

MSc Thesis

Bib PDF Code

@mastersthesis{Turan2022Msc,
  title = {Robustness of Hybrid Discriminative-Generative Models},
  author = {Turan, Berkant},
  year = {2022},
  school = {Technical University of Berlin},
  type = {mastersthesis},
}

Modeling and Simulation of Convective Flows in the Outer Earth’s Core using the Finite Element Method

Berkant Turan

Technical University of Berlin, Jul 2018

BSc Thesis

Bib PDF Code

@bachelorsthesis{Turan2018Bsc,
  title = {Modeling and Simulation of Convective Flows in the Outer Earth's Core using the Finite Element Method},
  author = {Turan, Berkant},
  year = {2018},
  school = {Technical University of Berlin},
  type = {mastersthesis},
}