{
  "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_shown": true,
  "affiliations": [],
  "article_type": "Journal reference: Proceedings of the 35th ACM International Conference on Information and Knowledge Management, 2026, Pages 7063 - 7068",
  "arxiv": "2605.28739",
  "author_total": 1,
  "authors": [
    {
      "name": "Tirtharaj Dash"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/ezspqye9zyj4a.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2605.28739",
  "fulltext_url": null,
  "id": "ezspqye9zyj4a",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2605.28739",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.AI"
    ],
    [
      "arxiv",
      "cs.LG"
    ],
    [
      "arxiv",
      "cs.NE"
    ],
    [
      "arxiv",
      "q-bio.QM"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2605.28739",
  "pmcid": null,
  "pmid": null,
  "published": "2026-08-23",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/ezspqye9zyj4a.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T15:21:30Z",
      "native_id": "2605.28739",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2605.28739"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "arxiv:q-bio.QM",
      "subfield": "bioinformatics"
    }
  ],
  "title": "BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks",
  "title_text": "BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks",
  "type": "preprint",
  "updated_at": "2026-11-06T18:21:04Z",
  "url": "https://research.draconitic.com/paper/ezspqye9zyj4a",
  "venue": "arXiv",
  "versions": [
    {
      "doi": "10.1145/3799682.383985",
      "pid": null,
      "relation": "published-as",
      "title": null,
      "venue": null
    }
  ]
}