BranchNet: A Neuro-Symbolic Learning Framework for Structured Multi-Class Classification

• URL: http://arxiv.org/abs/2507.01781v1
• Date: Wed, 02 Jul 2025 15:07:58 GMT
• Title: BranchNet: A Neuro-Symbolic Learning Framework for Structured Multi-Class Classification
• Abstract summary: We introduce BranchNet, a neuro-symbolic learning framework that transforms decision tree ensembles into sparse, partially connected neural networks.<n>The resulting models are compact, interpretable, and require no manual architecture tuning.
• Score: 7.38482187232142
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce BranchNet, a neuro-symbolic learning framework that transforms decision tree ensembles into sparse, partially connected neural networks. Each branch, defined as a decision path from root to a parent of leaves, is mapped to a hidden neuron, preserving symbolic structure while enabling gradient-based optimization. The resulting models are compact, interpretable, and require no manual architecture tuning. Evaluated on a suite of structured multi-class classification benchmarks, BranchNet consistently outperforms XGBoost in accuracy, with statistically significant gains. We detail the architecture, training procedure, and sparsity dynamics, and discuss the model's strengths in symbolic interpretability as well as its current limitations, particularly on binary tasks where further adaptive calibration may be beneficial.

Related papers

• Building a Neural Network from Scratch: Implementation, Evaluation, and Optimization [0.913755431537592]
  The paper presents a self-contained neural network framework implemented entirely from scratch.<n>The implementation encompasses all essential components, including multi-layer architectures, diverse activation functions, and state-of-the-art modularitys.
  arXiv  Detail & Related papers  (2026-07-18T07:31:59Z)
• Improving Set Function Approximation with Quasi-Arithmetic Neural Networks [23.73257235603082]
  We propose quasi-arithmetic neural networks (QUANNs)<n>QUANNs are universal approximators for a broad class of common set-function decompositions.<n>We provide a theoretical analysis showing that, QUANNs are universal approximators for a broad class of common set-function decompositions.
  arXiv  Detail & Related papers  (2026-02-04T18:36:31Z)
• Combining feature-based approaches with graph neural networks and symbolic regression for synergistic performance and interpretability [0.0]
  MatterVial is an innovative hybrid framework for feature-based machine learning in materials science.<n>Our approach combines the chemical transparency of traditional feature-based models with the predictive power of deep learning architectures.<n>An integrated interpretability module, employing surrogate models and symbolic regression, decodes the latent GNN-derived descriptors into explicit, physically meaningful formulas.
  arXiv  Detail & Related papers  (2025-09-02T16:45:02Z)
• Plastic tensor networks for interpretable generative modeling [0.0874967598360817]
  A single-layer nonnegative adaptive tensor tree (NATT) that models a target probability distribution is proposed as an alternative paradigm for generative modeling.<n>We consider the NATT scheme and a recently proposed Born machine adaptive tensor tree (BMATT) optimization scheme and demonstrate their effectiveness on a variety of generative modeling tasks.
  arXiv  Detail & Related papers  (2025-04-09T09:23:11Z)
• Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning [115.79349923044663]
  Few-shot class-incremental learning (FSCIL) aims to incrementally learn novel classes from limited examples.<n>Existing methods face a critical dilemma: static architectures rely on a fixed parameter space to learn from data that arrive sequentially, prone to overfitting to the current session.<n>In this study, we explore the potential of Selective State Space Models (SSMs) for FSCIL.
  arXiv  Detail & Related papers  (2024-07-08T17:09:39Z)
• Coding schemes in neural networks learning classification tasks [52.22978725954347]
  We investigate fully-connected, wide neural networks learning classification tasks. We show that the networks acquire strong, data-dependent features. Surprisingly, the nature of the internal representations depends crucially on the neuronal nonlinearity.
  arXiv  Detail & Related papers  (2024-06-24T14:50:05Z)
• Semantic Loss Functions for Neuro-Symbolic Structured Prediction [74.18322585177832]
  We discuss the semantic loss, which injects knowledge about such structure, defined symbolically, into training. It is agnostic to the arrangement of the symbols, and depends only on the semantics expressed thereby. It can be combined with both discriminative and generative neural models.
  arXiv  Detail & Related papers  (2024-05-12T22:18:25Z)
• DepGraph: Towards Any Structural Pruning [68.40343338847664]
  We study general structural pruning of arbitrary architecture like CNNs, RNNs, GNNs and Transformers. We propose a general and fully automatic method, emphDependency Graph (DepGraph), to explicitly model the dependency between layers and comprehensively group parameters for pruning. In this work, we extensively evaluate our method on several architectures and tasks, including ResNe(X)t, DenseNet, MobileNet and Vision transformer for images, GAT for graph, DGCNN for 3D point cloud, alongside LSTM for language, and demonstrate that, even with a
  arXiv  Detail & Related papers  (2023-01-30T14:02:33Z)
• Towards Understanding the Link Between Modularity and Performance in Neural Networks for Reinforcement Learning [2.038038953957366]
  We find that the amount of network modularity for optimal performance is likely entangled in complex relationships between many other features of the network and problem environment. We used a classic neuroevolutionary algorithm which enables rich, automatic optimisation and exploration of neural network architectures.
  arXiv  Detail & Related papers  (2022-05-13T05:18:18Z)
• Modeling Structure with Undirected Neural Networks [20.506232306308977]
  We propose undirected neural networks, a flexible framework for specifying computations that can be performed in any order. We demonstrate the effectiveness of undirected neural architectures, both unstructured and structured, on a range of tasks.
  arXiv  Detail & Related papers  (2022-02-08T10:06:51Z)
• Random Graph-Based Neuromorphic Learning with a Layer-Weaken Structure [4.477401614534202]
  We transform the random graph theory into an NN model with practical meaning and based on clarifying the input-output relationship of each neuron. Under the usage of this low-operation cost approach, neurons are assigned to several groups of which connection relationships can be regarded as uniform representations of random graphs they belong to. We develop a joint classification mechanism involving information interaction between multiple RGNNs and realize significant performance improvements in supervised learning for three benchmark tasks.
  arXiv  Detail & Related papers  (2021-11-17T03:37:06Z)
• Sparsely ensembled convolutional neural network classifiers via reinforcement learning [0.0]
  We consider convolutional neural network (CNN) ensemble learning with the objective function inspired by least action principle. We teach an agent to perceive images through the set of pre-trained classifiers and want the resulting dynamically configured system to unfold the computational graph. Our experimental results prove, that if the agent exploits the dynamic (and context-dependent) structure of computations, it outperforms conventional ensemble learning.
  arXiv  Detail & Related papers  (2021-02-07T21:26:57Z)
• A Semi-Supervised Assessor of Neural Architectures [157.76189339451565]
  We employ an auto-encoder to discover meaningful representations of neural architectures. A graph convolutional neural network is introduced to predict the performance of architectures.
  arXiv  Detail & Related papers  (2020-05-14T09:02:33Z)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)

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.