Martin Jullum

24 papers C 1Journal 19Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
How important are the genes to explain the outcome - the asymmetric Shapley value as an honest importance metric for high-dimensional features.
CoRR
Mark A. van de Wiel, Jeroen M. Goedhart, Martin Jullum, Kjersti Aas
2025 J jnl
AI/ML for 5G and Beyond Cybersecurity.
CoRR
Sandeep Pirbhulal, Habtamu Abie, Martin Jullum, Didrik Nielsen, Anders Løland
2025 — conf
Improving the Weighting Strategy in KernelSHAP.
xAI (2)
Lars Henry Berge Olsen, Martin Jullum
2025 — conf
What's Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models.
xAI (3)
Jan Kapar, Niklas Koenen, Martin Jullum
2025 J jnl
What's Wrong with Your Synthetic Tabular Data? Using Explainable AI to Evaluate Generative Models.
CoRR
Jan Kapar, Niklas Koenen, Martin Jullum
2025 J jnl
shapr: Explaining Machine Learning Models with Conditional Shapley Values in R and Python.
CoRR
Martin Jullum, Lars Henry Berge Olsen, Jon Lachmann, Annabelle Redelmeier
2024 J jnl
A comparative study of methods for estimating model-agnostic Shapley value explanations.
Data Min. Knowl. Discov.
Lars Henry Berge Olsen, Ingrid Kristine Glad, Martin Jullum, Kjersti Aas
2024 J jnl
Improving the Sampling Strategy in KernelSHAP.
CoRR
Lars Henry Berge Olsen, Martin Jullum
2024 J jnl
MCCE: Monte Carlo sampling of valid and realistic counterfactual explanations for tabular data.
Data Min. Knowl. Discov.
Annabelle Redelmeier, Martin Jullum, Kjersti Aas, Anders Løland
2023 J jnl
A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them.
CoRR
Lars Henry Berge Olsen, Ingrid Kristine Glad, Martin Jullum, Kjersti Aas
2023 J jnl
Finding Money Launderers Using Heterogeneous Graph Neural Networks.
CoRR
Fredrik Johannessen, Martin Jullum
2023 — conf
eXplego: An interactive Tool that Helps you Select Appropriate XAI-methods for your Explainability Needs.
xAI (Late-breaking Work, Demos, Doctoral Consortium)
Martin Jullum, Jacob Sjødin, Robindra Prabhu, Anders Løland
2022 J jnl
Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features.
J. Mach. Learn. Res.
Lars H. B. Olsen, Ingrid Kristine Glad, Martin Jullum, Kjersti Aas
2021 — conf
Comparison of Contextual Importance and Utility with LIME and Shapley Values.
EXTRAAMAS@AAMAS
Kary Främling, Marcus Westberg, Martin Jullum, Manik Madhikermi, Avleen Malhi
2021 J jnl
Explaining individual predictions when features are dependent: More accurate approximations to Shapley values.
Artif. Intell.
Kjersti Aas, Martin Jullum, Anders Løland
2021 J jnl
Explaining predictive models using Shapley values and non-parametric vine copulas.
CoRR
Kjersti Aas, Thomas Nagler, Martin Jullum, Anders Løland
2021 J jnl
MCCE: Monte Carlo sampling of realistic counterfactual explanations.
CoRR
Annabelle Redelmeier, Martin Jullum, Kjersti Aas, Anders Løland
2021 J jnl
Statistical embedding: Beyond principal components.
CoRR
Dag Tjøstheim, Martin Jullum, Anders Løland
2021 J jnl
Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Features.
CoRR
Lars Henry Berge Olsen, Ingrid Kristine Glad, Martin Jullum, Kjersti Aas
2021 J jnl
groupShapley: Efficient prediction explanation with Shapley values for feature groups.
CoRR
Martin Jullum, Annabelle Redelmeier, Kjersti Aas
2020 C conf
Explaining Predictive Models with Mixed Features Using Shapley Values and Conditional Inference Trees.
CD-MAKE
Annabelle Redelmeier, Martin Jullum, Kjersti Aas
2020 J jnl
Explaining predictive models with mixed features using Shapley values and conditional inference trees.
CoRR
Annabelle Redelmeier, Martin Jullum, Kjersti Aas
2019 J jnl
Explaining individual predictions when features are dependent: More accurate approximations to Shapley values.
CoRR
Kjersti Aas, Martin Jullum, Anders Løland
2019 J jnl
shapr: An R-package for explaining machine learning models with dependence-aware Shapley values.
J. Open Source Softw.
Nikolai Sellereite, Martin Jullum