BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks
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× 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.
Versions
Related
- Heterogeneous graph neural networks with biological prior knowledge for interpretable drug repurposing in triple-negative breast cancer
- Img2EEG: A Scalable and Interpretable Encoding Framework for Simulating Human EEG Responses to Visual Inputs
- Interpretable embeddings of speech explain and enhance the brain encoding performance of audio models
- Learning interpretable kinetic models for biomolecular interaction networks
- Encoding level-3 semi-directed phylogenetic networks by quarnets and quinnets
BibTeX
@misc{dash2026birdnet,
title = {{BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks}},
author = {Tirtharaj Dash},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2605.28739},
eprint = {2605.28739},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.28739},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks
AU - Tirtharaj Dash
PY - 2026
DA - 2026/08/23
PB - arXiv
DO - 10.48550/arxiv.2605.28739
UR - https://arxiv.org/abs/2605.28739
AB - 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× 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.
ER -