Beyond Graph Neural Networks with Lifted Relational Neural Networks

by   Gustav Sourek, et al.

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.


page 24

page 25


Improving the Long-Range Performance of Gated Graph Neural Networks

Many popular variants of graph neural networks (GNNs) that are capable o...

Learning with Molecules beyond Graph Neural Networks

We demonstrate a deep learning framework which is inherently based in th...

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

Graph neural networks (GNNs) have emerged as a powerful tool for learnin...

Lossless Compression of Structured Convolutional Models via Lifting

Lifting is an efficient technique to scale up graphical models generaliz...

Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings

We propose ArtSAGENet, a novel multimodal architecture that integrates G...

Differentiable Reasoning over Long Stories – Assessing Systematic Generalisation in Neural Models

Contemporary neural networks have achieved a series of developments and ...

On Representing Linear Programs by Graph Neural Networks

Learning to optimize is a rapidly growing area that aims to solve optimi...

Code Repositories


Deep relational learning through differentiable logic programming.

view repo