Localizing predictive concepts encoded in neural representations via hierarchical testing

arXiv:2610.41046v1 Announce Type: new Abstract: Understanding which regulatory sequence motifs a genomic deep learning model has learned, with statistical error guarantees, is essential for trusting its use in downstream tasks such as variant effect prediction. Existing approaches to identifying which units in a trained network encode human- understandable concepts fall into two groups. Exploratory methods rank and visualize units but offer no statistical guarantee that the selected units are associated with the prediction target across the population of inputs. Testing-based methods test only single units or one pre-defined set of them, and do not control the error across the many sets of units.