95 citations · 95 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Structural Compositional Function Networks: Interpretable Functional Compositions for Tabular Discovery
Fang Li
Despite the ubiquity of tabular data in high-stakes domains, traditional deep learning architectures often struggle to match the performance of gradient-boosted decision trees whil…
cs.LG2025
Compositional Function Networks: A High-Performance Alternative to Deep Neural Networks with Built-in Interpretability
Fang Li
Deep Neural Networks (DNNs) deliver impressive performance but their black-box nature limits deployment in high-stakes domains requiring transparency. We introduce Compositional Fu…