DeepGraphLog for Layered Neurosymbolic AI

2025-09-09

AI Summary

Existing neuro-symbolic AI frameworks (e.g., DeepProbLog) enforce a rigid, sequential pipeline where neural processing must precede symbolic reasoning, limiting their ability to model complex, irregular structural dependencies—especially in graph-structured data. Method: We propose DeepGraphLog, the first neuro-symbolic framework supporting arbitrary-order, multi-layer interaction between neural and symbolic components. Its core innovation is modeling symbolic representations as graphs and unifying their processing via graph neural networks (GNNs), introducing *graph neural predicates* to enable bidirectional message passing and composable, hierarchical reasoning. DeepGraphLog integrates ProbLog’s probabilistic logic programming with GNNs, breaking the conventional unidirectional pipeline paradigm. Contribution/Results: Evaluated on planning, distantly supervised knowledge graph completion, and GNN expressivity assessment, DeepGraphLog significantly improves modeling of higher-order relational dependencies and extends the applicability boundary of neuro-symbolic AI to graph-structured domains.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Knowledge Representation and Reasoning: Logic Programming
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Neurosymbolic AI (NeSy) aims to integrate the statistical strengths of neural networks with the interpretability and structure of symbolic reasoning. However, current NeSy frameworks like DeepProbLog enforce a fixed flow where symbolic reasoning always follows neural processing. This restricts their ability to model complex dependencies, especially in irregular data structures such as graphs. In this work, we introduce DeepGraphLog, a novel NeSy framework that extends ProbLog with Graph Neural Predicates. DeepGraphLog enables multi-layer neural-symbolic reasoning, allowing neural and symbolic components to be layered in arbitrary order. In contrast to DeepProbLog, which cannot handle symbolic reasoning via neural methods, DeepGraphLog treats symbolic representations as graphs, enabling them to be processed by Graph Neural Networks (GNNs). We showcase the capabilities of DeepGraphLog on tasks in planning, knowledge graph completion with distant supervision, and GNN expressivity. Our results demonstrate that DeepGraphLog effectively captures complex relational dependencies, overcoming key limitations of existing NeSy systems. By broadening the applicability of neurosymbolic AI to graph-structured domains, DeepGraphLog offers a more expressive and flexible framework for neural-symbolic integration.

Problem

• Extends neurosymbolic AI to handle graph-structured data
• Enables flexible layering of neural and symbolic components
• Overcomes limitations of fixed neural-symbolic processing flow

Innovation

• Layered neural-symbolic reasoning with arbitrary ordering
• Graph Neural Predicates extend ProbLog framework
• Symbolic representations processed as graphs via GNNs