Not all tickets are equal and we know it: Guiding pruning with domain-specific knowledge

arXiv:2403.04805v1 Announce Type: new
Abstract: Neural structure learning is of paramount importance for scientific discovery and interpretability. Yet, contemporary pruning algorithms that focus on computational resource efficiency face algorithmic barriers to select a meaningful model that aligns with domain expertise. To mitigate this challenge, we propose DASH, which guides pruning by available domain-specific structural information. In the context of learning dynamic gene regulatory network models, we show that DASH combined with existing general knowledge on interaction partners provides data-specific insights …

abstract algorithms arxiv challenge computational cs.lg discovery domain efficiency expertise face focus importance interpretability knowledge pruning q-bio.qm resource efficiency scientific discovery stat.ap stat.ml tickets type