Mateusz Gajewski

According to our database, Mateusz Gajewski authored at least 3 papers in 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2025

VARSHAP: Addressing Global Dependency Problems in Explainable AI with Variance-Based Local Feature Attribution.

Mateusz Gajewski, Mikolaj Morzy, Adam Karczmarz, Piotr Sankowski

CoRR, June, 2025

Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery.

Mateusz Olko, Mateusz Gajewski, Joanna Wojciechowska, Mikolaj Morzy, Piotr Sankowski, Piotr Milos

CoRR, February, 2025

Accurate Estimation of Feature Importance Faithfulness for Tree Models.

Mateusz Gajewski, Adam Karczmarz, Mateusz Rapicki, Piotr Sankowski

Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025