DeepGraphLog for Layered Neurosymbolic AI

• URL: http://arxiv.org/abs/2509.07665v1
• Date: Tue, 09 Sep 2025 12:32:07 GMT
• Title: DeepGraphLog for Layered Neurosymbolic AI
• Abstract summary: We introduce DeepGraphLog, a novel NeSy framework that extends ProbLog with Graph Neural Predicates.<n>DeepGraphLog treats symbolic representations as graphs, enabling them to be processed by Graph Neural Networks (GNNs)
• Score: 26.481541418952858
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Superhypergraph Neural Networks and Plithogenic Graph Neural Networks: Theoretical Foundations [0.0]
  Hypergraphs extend traditional graphs by allowing edges to connect multiple nodes, while superhypergraphs further generalize this concept to represent even more complex relationships.<n>Graph Neural Networks (GNNs), a well-established framework, have recently been extended to Hypergraph Neural Networks (HGNNs)<n>This paper establishes the theoretical foundation for the development of SuperHyperGraph Neural Networks (SHGNNs) and Plithogenic Graph Neural Networks.
  arXiv  Detail & Related papers  (2024-12-02T06:33:02Z)
• Temporal Spiking Neural Networks with Synaptic Delay for Graph Reasoning [91.29876772547348]
  Spiking neural networks (SNNs) are investigated as biologically inspired models of neural computation. This paper reveals that SNNs, when amalgamated with synaptic delay and temporal coding, are proficient in executing (knowledge) graph reasoning.
  arXiv  Detail & Related papers  (2024-05-27T05:53:30Z)
• The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning [54.56905063752427]
  Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI systems. Existing pipelines that train the neural and symbolic components sequentially require extensive labelling. New architecture, NeSyGPT, fine-tunes a vision-language foundation model to extract symbolic features from raw data.
  arXiv  Detail & Related papers  (2024-02-02T20:33:14Z)
• DepWiGNN: A Depth-wise Graph Neural Network for Multi-hop Spatial Reasoning in Text [52.699307699505646]
  We propose a novel Depth-Wise Graph Neural Network (DepWiGNN) to handle multi-hop spatial reasoning. Specifically, we design a novel node memory scheme and aggregate the information over the depth dimension instead of the breadth dimension of the graph. Experimental results on two challenging multi-hop spatial reasoning datasets show that DepWiGNN outperforms existing spatial reasoning methods.
  arXiv  Detail & Related papers  (2023-10-19T08:07:22Z)
• Knowledge Enhanced Graph Neural Networks for Graph Completion [0.0]
  Knowledge Enhanced Graph Neural Networks (KeGNN) is a neuro-symbolic framework for graph completion. KeGNN consists of a graph neural network as a base upon which knowledge enhancement layers are stacked. We instantiate KeGNN in conjunction with two state-of-the-art graph neural networks, Graph Convolutional Networks and Graph Attention Networks.
  arXiv  Detail & Related papers  (2023-03-27T07:53:43Z)
• Transferability Properties of Graph Neural Networks [125.71771240180654]
  Graph neural networks (GNNs) are provably successful at learning representations from data supported on moderate-scale graphs. We study the problem of training GNNs on graphs of moderate size and transferring them to large-scale graphs. Our results show that (i) the transference error decreases with the graph size, and (ii) that graph filters have a transferability-discriminability tradeoff that in GNNs is alleviated by the scattering behavior of the nonlinearity.
  arXiv  Detail & Related papers  (2021-12-09T00:08:09Z)
• deepstruct -- linking deep learning and graph theory [1.4504054468850667]
  deepstruct connects deep learning models and graph theory. Deepstruct provides deep neural network models with different restrictions which can be created based on an initial graph.
  arXiv  Detail & Related papers  (2021-11-12T11:58:13Z)
• Learning through structure: towards deep neuromorphic knowledge graph embeddings [0.5906031288935515]
  We propose a strategy to map deep graph learning architectures for knowledge graph reasoning to neuromorphic architectures. Based on the insight that randomly and untrained graph neural networks are able to preserve local graph structures, we compose a frozen neural network shallow knowledge graph embedding models. We experimentally show that already on conventional computing hardware, this leads to a significant speedup and memory reduction while maintaining a competitive performance level.
  arXiv  Detail & Related papers  (2021-09-21T18:01:04Z)
• Graph Neural Networks for Graph Drawing [17.983238300054527]
  We propose a novel framework for the development of Graph Neural Drawers (GND) GNDs rely on neural computation for constructing efficient and complex maps. We prove that this mechanism can be guided by loss functions computed by means of Feedforward Neural Networks.
  arXiv  Detail & Related papers  (2021-09-21T09:58:02Z)
• Increase and Conquer: Training Graph Neural Networks on Growing Graphs [116.03137405192356]
  We consider the problem of learning a graphon neural network (WNN) by training GNNs on graphs sampled Bernoulli from the graphon. Inspired by these results, we propose an algorithm to learn GNNs on large-scale graphs that, starting from a moderate number of nodes, successively increases the size of the graph during training.
  arXiv  Detail & Related papers  (2021-06-07T15:05:59Z)
• Graph and graphon neural network stability [122.06927400759021]
  Graph networks (GNNs) are learning architectures that rely on knowledge of the graph structure to generate meaningful representations of network data. We analyze GNN stability using kernel objects called graphons.
  arXiv  Detail & Related papers  (2020-10-23T16:55:56Z)
• Graph Structure of Neural Networks [104.33754950606298]
  We show how the graph structure of neural networks affect their predictive performance. A "sweet spot" of relational graphs leads to neural networks with significantly improved predictive performance. Top-performing neural networks have graph structure surprisingly similar to those of real biological neural networks.
  arXiv  Detail & Related papers  (2020-07-13T17:59:31Z)

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.