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

• URL: http://arxiv.org/abs/2605.28739v1
• Date: Wed, 27 May 2026 16:59:01 GMT
• Title: BIRDNet: Mining and Encoding Boolean Implication Knowledge Graphs as Interpretable Deep Neural Networks
• Abstract summary: We encode a graph as the connectivity of a layered neural network, called BIRDNet.<n>Each hidden unit corresponds to one mined rule and binds only to its two features.<n>We evaluate BIRDNet on six transcriptomic and proteomic benchmarks.
• Score: 1.200935710020835
• License: http://creativecommons.org/licenses/by/4.0/
• 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. The mined implications form a typed directed graph, equivalent to a propositional rule base of 2-literal clauses. We encode this 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 by construction: at most $2/d$ of the weights in each BIR layer are active, where $d$ is the input dimension. Second, the model is 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, at a small accuracy cost, while using up to $96\times$ fewer active parameters than an architecture-matched dense MLP. First-layer rules recover known biological signatures across multiple cancer subtypes and tissue types, including canonical amplicons, lineage-defining co-expression modules, and immune-infiltration markers. Data and code are available at: https://github.com/MAHI-Group/BIRDNet.

Related papers

• Probabilistic Salary Prediction with Graph Attention Networks and a Mixture Density Network [0.0]
  We propose GAT-MDN, a unified framework that addresses both limitations simultaneously.<n>For each of the three attribute domains we construct a domain-specific graph whose edges encode (i) hierarchical parent-child containment and (ii) weighted similarity links derived from a pre-trained Sentence-Transformer.<n>Experiments on a real-world Dutch job-posting dataset of over 1 million records demonstrate that GAT-MDN significantly outperforms a non-graph-MDN baseline in both Negative Log-Likelihood (NLL) and Mean Squared Error (MSE)
  arXiv  Detail & Related papers  (2026-06-10T05:12:29Z)
• A Tight Expressivity Hierarchy for GNN-Based Entity Resolution in Master Data Management [2.4366811507669115]
  We prove a four-theorem separation theory on typed entity-attribute graphs.<n>For each predicate we prove tight bounds -- constructing graph pairs provably indistinguishable by every MPNN lacking the required adaptation.<n>Results yield a minimal-architecture principle: practitioners can select the cheapest sufficient adaptation set, with a guarantee that no simpler architecture works.
  arXiv  Detail & Related papers  (2026-03-28T06:38:03Z)
• M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling [53.351103753419046]
  We introduce Matrix-to-Matrix RNN: an architecture with matrix-valued hidden states and expressive non-linear state transitions.<n>We demonstrate that the language modeling performance of non-linear RNNs is limited by their state size.<n>We also demonstrate how the state size expansion mechanism enables efficient use of tensor cores.
  arXiv  Detail & Related papers  (2026-03-15T12:53:09Z)
• Structurally Human, Semantically Biased: Detecting LLM-Generated References with Embeddings and GNNs [7.158582263989492]
  We build paired citation graphs, ground truth and GPT-4o-generated (from parametric knowledge) for 10,000 papers from SciSciNet.<n>We show that GPT barely separates from ground truth (RF accuracy $approx$ 0.60) despite cleanly rejecting the random baseline.<n> embeddings sharply increase separability: RF on aggregated embeddings reaches $approx$ 0.83, and GNNs with embedding node features achieve 93% test accuracy on GPT vs. ground truth.
  arXiv  Detail & Related papers  (2026-01-28T15:37:31Z)
• WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks [2.3612692427322313]
  We propose WGLE, a novel black-box watermarking paradigm for Graph Neural Networks (GNNs)<n>WGLE embeds the watermark encoding the intended information without introducing incorrect mappings that compromise the primary task.<n>Results show that WGLE achieves 100% ownership verification accuracy, an average fidelity of 0.85%, comparable against potential attacks, and low embedding overhead.
  arXiv  Detail & Related papers  (2025-06-10T09:12:00Z)
• RBA-GCN: Relational Bilevel Aggregation Graph Convolutional Network for Emotion Recognition [38.87080348908327]
  We present the relational bilevel aggregation graph convolutional network (RBA-GCN) It consists of three modules: the graph generation module (GGM), similarity-based cluster building module (SCBM) and bilevel aggregation module (BiAM) On both the IEMOCAP and MELD datasets, the weighted average F1 score of RBA-GCN has a 2.17$sim$5.21% improvement over that of the most advanced method.
  arXiv  Detail & Related papers  (2023-08-18T11:29:12Z)
• Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies [52.691032025163175]
  Existing Binary Neural Networks (BNNs) operate mainly on local convolutions with binarization function. We present new designs of binary neural modules, which enables leading binary neural modules by a large margin.
  arXiv  Detail & Related papers  (2022-09-03T11:51:04Z)
• Robust Training and Verification of Implicit Neural Networks: A Non-Euclidean Contractive Approach [64.23331120621118]
  This paper proposes a theoretical and computational framework for training and robustness verification of implicit neural networks. We introduce a related embedded network and show that the embedded network can be used to provide an $ell_infty$-norm box over-approximation of the reachable sets of the original network. We apply our algorithms to train implicit neural networks on the MNIST dataset and compare the robustness of our models with the models trained via existing approaches in the literature.
  arXiv  Detail & Related papers  (2022-08-08T03:13:24Z)
• A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features [61.92791503017341]
  Graph Neural Networks (GNNs) with numerical node features and graph structure as inputs have demonstrated superior performance on various supervised learning tasks with graph data. The best models for such data types in most standard supervised learning settings with IID (non-graph) data are not easily incorporated into a GNN. Here we propose a robust stacking framework that fuses graph-aware propagation with arbitrary models intended for IID data.
  arXiv  Detail & Related papers  (2022-06-16T22:46:33Z)
• Mixed Graph Contrastive Network for Semi-Supervised Node Classification [63.924129159538076]
  We propose a novel graph contrastive learning method, termed Mixed Graph Contrastive Network (MGCN)<n>In our method, we improve the discriminative capability of the latent embeddings by an unperturbed augmentation strategy and a correlation reduction mechanism.<n>By combining the two settings, we extract rich supervision information from both the abundant nodes and the rare yet valuable labeled nodes for discriminative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• RU-Net: Regularized Unrolling Network for Scene Graph Generation [92.95032610978511]
  Scene graph generation (SGG) aims to detect objects and predict the relationships between each pair of objects. Existing SGG methods usually suffer from several issues, including 1) ambiguous object representations, and 2) low diversity in relationship predictions. We propose a regularized unrolling network (RU-Net) to address both problems.
  arXiv  Detail & Related papers  (2022-05-03T04:21:15Z)
• Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks [127.32203532517953]
  We develop a vanilla 1-bit framework that binarizes both the GNN parameters and the graph features. Despite the lightweight architecture, we observed that this vanilla framework suffered from insufficient discriminative power in distinguishing graph topologies. This discovery motivates us to devise meta aggregators to improve the expressive power of vanilla binarized GNNs.
  arXiv  Detail & Related papers  (2021-09-27T08:50:37Z)
• A Law of Robustness for Weight-bounded Neural Networks [37.54604146791085]
  Recently, (Bubeck et al., 2020) conjectured that when using two-layer networks with $k$ neurons to fit a generic dataset, the smallest Lipschitz constant is $Omega(sqrtfracnk)$. In this work we derive a lower bound on the Lipschitz constant for any arbitrary model class with bounded Rademacher complexity. Our result coincides with that conjectured in (Bubeck et al., 2020) for two-layer networks under the assumption of bounded weights.
  arXiv  Detail & Related papers  (2021-02-16T11:28:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.