DeepGraphLog for Layered Neurosymbolic AI
This work addresses the problem of modeling complex dependencies in irregular data structures like graphs for researchers and practitioners in neurosymbolic AI, offering a more flexible framework, though it appears incremental as an extension of existing systems.
The paper tackled the limitation of fixed neural-symbolic flows in neurosymbolic AI by introducing DeepGraphLog, a framework that enables multi-layer neural-symbolic reasoning with arbitrary ordering, and demonstrated its effectiveness in capturing complex relational dependencies in tasks like planning and knowledge graph completion.
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.