Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Preserving Task-Relevant Information Under Linear Concept Removal
Floris Holstege, Shauli Ravfogel, Bram Wouters
Modern neural networks often encode unwanted concepts alongside task-relevant information, leading to fairness and interpretability concerns. Existing post-hoc approaches can remov…
cs.LG2024
Removing Spurious Concepts from Neural Network Representations via Joint Subspace Estimation
Floris Holstege, Bram Wouters, Noud van Giersbergen +1
Out-of-distribution generalization in neural networks is often hampered by spurious correlations. A common strategy is to mitigate this by removing spurious concepts from the neura…