# Beyond Graph Neural Networks with Lifted Relational Neural Networks

arXiv: https://arxiv.org/abs/2007.06286 · HTML: https://mlsanity.com/paper/2007.06286/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [Incorporating Domain Knowledge into Deep Neural Networks](https://mlsanity.com/paper/2103.00180/) (2021)
- [On the Correspondence Between Monotonic Max-Sum GNNs and Datalog](https://mlsanity.com/paper/2305.18015/) (2023)
- [Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment](https://mlsanity.com/paper/2105.10709/) (2021)
- [Systematic Relational Reasoning With Epistemic Graph Neural Networks](https://mlsanity.com/paper/2407.17396/) (2024)
- [Deep Learning for Generalised Planning with Background Knowledge](https://mlsanity.com/paper/2410.07923/) (2024)
- [A Neuro-Symbolic Approach for Probabilistic Reasoning on Graph Data](https://mlsanity.com/paper/2507.21873/) (2025)
- [DeepGraphLog for Layered Neurosymbolic AI](https://mlsanity.com/paper/2509.07665/) (2025)
- [A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks](https://mlsanity.com/paper/2107.10295/) (2021)

## Abstract (arXiv)

We demonstrate a declarative differentiable programming framework based on the language of Lifted Relational Neural Networks, where small parameterized logic programs are used to encode relational learning scenarios. When presented with relational data, such as various forms of graphs, the program interpreter dynamically unfolds differentiable computational graphs to be used for the program parameter optimization by standard means. Following from the used declarative Datalog abstraction, this results into compact and elegant learning programs, in contrast with the existing procedural approaches operating directly on the computational graph level. We illustrate how this idea can be used for an efficient encoding of a diverse range of existing advanced neural architectures, with a particular focus on Graph Neural Networks (GNNs). Additionally, we show how the contemporary GNN models can be easily extended towards higher relational expressiveness. In the experiments, we demonstrate correctness and computation efficiency through comparison against specialized GNN deep learning frameworks, while shedding some light on the learning performance of existing GNN models.