Neurosymbolic Decision Trees

2025-03-11

AI Summary

Neural-symbolic models face challenges in learning interpretable symbolic structures from sub-symbolic data. Method: This paper proposes the Interpretable Neural Decision Tree (NDT) and its structure-learning algorithm, NeuID3. NeuID3 explicitly incorporates logical prior knowledge into decision tree induction by unifying DeepProbLog’s probabilistic logic representation with a topologically enhanced ID3 induction mechanism, enabling joint optimization of neural components (for processing sub-symbolic inputs such as images) and symbolic components (logic rules). Contribution/Results: Compared to purely neural approaches, NDT achieves significantly improved generalization, few-shot reasoning capability, and interpretability on multi-class symbol-visual hybrid tasks. It preserves structural readability—enabling human-understandable rule extraction—while maintaining perceptual robustness against input perturbations.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Computer Vision: Visual Reasoning & Symbolic Representations
• Cognitive Modeling & Cognitive Systems: Symbolic Representations

Application Category

• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Neurosymbolic (NeSy) AI studies the integration of neural networks (NNs) and symbolic reasoning based on logic. Usually, NeSy techniques focus on learning the neural, probabilistic and/or fuzzy parameters of NeSy models. Learning the symbolic or logical structure of such models has, so far, received less attention. We introduce neurosymbolic decision trees (NDTs), as an extension of decision trees together with a novel NeSy structure learning algorithm, which we dub NeuID3. NeuID3 adapts the standard top-down induction of decision tree algorithms and combines it with a neural probabilistic logic representation, inherited from the DeepProbLog family of models. The key advantage of learning NDTs with NeuID3 is the support of both symbolic and subsymbolic data (such as images), and that they can exploit background knowledge during the induction of the tree structure, In our experimental evaluation we demonstrate the benefits of NeSys structure learning over more traditonal approaches such as purely data-driven learning with neural networks.

Problem

• Integrates neural networks with symbolic reasoning for AI models.
• Focuses on learning symbolic structure in neurosymbolic models.
• Supports symbolic and subsymbolic data using background knowledge.

Innovation

• Neurosymbolic decision trees integrate neural and symbolic reasoning.
• NeuID3 algorithm combines decision trees with neural probabilistic logic.
• Supports symbolic and subsymbolic data with background knowledge.