BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks

arXiv:2605.28739v2 Announce Type: replace-cross Abstract: Tabular data in knowledge-rich domains often carries a latent prior in the form of Boolean implication relationships (BIRs) between pairs of features. We mine such relationships with a sparse-exception binomial test. We encode the resulting typed graph as the connectivity of a layered neural network, called BIRDNet, in which each hidden unit corresponds to one mined rule and binds only to its two features. We show two consequences of this design: First, the architecture is sparse: at most $2/d$ of the weights in each BIR layer are active, where $d$ is the input dimension. Second, the model is intrinsically interpretable: every trained unit keeps a stable symbolic identity, so rules can be read off the network without surrogate models. Unlike most neurosymbolic models, BIRDNet does not consume an external rule base; its structural prior is mined from the data. We evaluate BIRDNet on six transcriptomic and proteomic benchmarks. Our results show that BIRDNet stays within $0.02$ AUROC of the strongest dense baseline, while using up to $95\times$ fewer active parameters than an architecture-matched dense MLP. First-layer rules align with known biological signatures across multiple cancer subtypes and tissue types. Matched-topology controls show that the mined graph contributes symbolic meaning rather than predictive advantage: shuffled or random pairings match or improve AUROC but no longer correspond to mined implications. Data and code are available at: https://github.com/MAHI-Group/BIRDNet.

Abstract:Tabular data in knowledge-rich domains often carries a latent prior in the form of Boolean implication relationships (BIRs) between pairs of features. We mine such relationships with a sparse-exception binomial test. We encode the resulting typed graph as the connectivity of a layered neural network, called BIRDNet, in which each hidden unit corresponds to one mined rule and binds only to its two features. We show two consequences of this design: First, the architecture is sparse: at most $2/d$ of the weights in each BIR layer are active, where $d$ is the input dimension. Second, the model is intrinsically interpretable: every trained unit keeps a stable symbolic identity, so rules can be read off the network without surrogate models. Unlike most neurosymbolic models, BIRDNet does not consume an external rule base; its structural prior is mined from the data. We evaluate BIRDNet on six transcriptomic and proteomic benchmarks. Our results show that BIRDNet stays within $0.02$ AUROC of the strongest dense baseline, while using up to $95\times$ fewer active parameters than an architecture-matched dense MLP. First-layer rules align with known biological signatures across multiple cancer subtypes and tissue types. Matched-topology controls show that the mined graph contributes symbolic meaning rather than predictive advantage: shuffled or random pairings match or improve AUROC but no longer correspond to mined implications. Data and code are available at: this https URL.

Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE); Quantitative Methods (q-bio.QM)

arXiv:2605.28739 [cs.LG]

(or arXiv:2605.28739v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.28739 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks

Related coverage