mlsanityData to 14 Oct 2026

Graph Reasoning Networks

arXiv 2407.05816 ↗First posted 8 Jul 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) are the predominant approach for graph-based machine learning. While neural networks have shown great performance at learning useful representations, they are often criticized for their limited high-level reasoning abilities. In this work, we present Graph Reasoning Networks (GRNs), a novel approach to combine the strengths of fixed and learned graph representations and a reasoning module based on a differentiable satisfiability solver. While results on real-world datasets show comparable performance to GNN, experiments on synthetic datasets demonstrate the potential of the newly proposed method.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 13 of its 17 references that are in the map. First posted on arXiv 8 Jul 2024.

Builds on

13 of 17 references.

References · 13

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
  5. 2018Neural Relational Inference for Interacting Systemscited by 339
  6. 2020Neurosymbolic AI: The 3rd Wavecited by 255
  7. 2020Can Graph Neural Networks Count Substructures?cited by 236
  8. 2021Weisfeiler and Lehman Go Cellular: CW Networkscited by 218
  9. 2017Learning Explanatory Rules from Noisy Datacited by 211
  10. 2019What graph neural networks cannot learn: depth vs widthcited by 201
  11. 2019SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solvercited by 173
  12. 2018DeepLogic: Towards End-to-End Differentiable Logical Reasoningcited by 8
1 more
  1. 2018Low-rank semidefinite programming for the MAX2SAT problemcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022Graph Neural Networks for Propositional Model Counting
  2. 2024Systematic Relational Reasoning With Epistemic Graph Neural Networks
  3. 2026Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer
  4. 2023Graph Agent: Explicit Reasoning Agent for Graphs
  5. 2025Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoning
  6. 2025Improving LLMs' Generalized Reasoning Abilities by Graph Problems
  7. 2025A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data
  8. 2025Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation