4 papers
Bayesian Flow Networks for Offline Trajectory Planning
Ludvig Killingberg, Helge Langseth
Offline reinforcement learning (RL) leverages static datasets to learn decision policies without real-time environment interaction. While recent sequence-modeling approaches rely o…
Exploring How Fair Model Representations Relate to Fair Recommendations
Bjørnar Vassøy, Benjamin Kille, Helge Langseth
One of the many fairness definitions pursued in recent recommender system research targets mitigating demographic information encoded in model representations. Models optimized for…
A Framework for Causal Concept-based Model Explanations
Anna Rodum Bjøru, Jacob Lysnæs-Larsen, Oskar Jørgensen +2
This work presents a conceptual framework for causal concept-based post-hoc Explainable Artificial Intelligence (XAI), based on the requirements that explanations for non-interpret…
Regularizing Explanations in Bayesian Convolutional Neural Networks
Yanzhe Bekkemoen, Helge Langseth
Neural networks are powerful function approximators with tremendous potential in learning complex distributions. However, they are prone to overfitting on spurious patterns. Bayesi…