
Beyond Graph Neural Networks with Lifted Relational Neural Networks
We demonstrate a declarative differentiable programming framework based ...
read it

Molecular MechanicsDriven Graph Neural Network with Multiplex Graph for Molecular Structures
The prediction of physicochemical properties from molecular structures i...
read it

On Graph Neural Network Ensembles for LargeScale Molecular Property Prediction
In order to advance largescale graph machine learning, the Open Graph B...
read it

Symbolic Relational Deep Reinforcement Learning based on Graph Neural Networks
We present a novel deep reinforcement learning framework for solving rel...
read it

Adversarial Model Extraction on Graph Neural Networks
Along with the advent of deep neural networks came various methods of ex...
read it

Lifted Relational Neural Networks
We propose a method combining relationallogic representations with neur...
read it

Neural Markov Logic Networks
We introduce Neural Markov Logic Networks (NMLNs), a statistical relatio...
read it
Learning with Molecules beyond Graph Neural Networks
We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how Graph Neural Networks and similar models can be easily covered in the framework by specifying the underlying propagation rules in the relational logic. The declarative nature of the used language then allows to easily modify and extend the propagation schemes into complex structures, such as the molecular rings which we choose for a short demonstration in this paper.
READ FULL TEXT
Comments
There are no comments yet.