Edge-similarity-aware Graph Neural Networks
This work addresses a domain-specific problem in computational biology by proposing a method to leverage edge similarities in graphs, though it is incremental as it builds on existing GNN frameworks without achieving performance gains.
The authors tackled the problem of incorporating edge similarity priors into Graph Neural Networks for tasks like RNA structure prediction, but found that including this prior did not improve empirical performance on their datasets.
Graph are a ubiquitous data representation, as they represent a flexible and compact representation. For instance, the 3D structure of RNA can be efficiently represented as $\textit{2.5D graphs}$, graphs whose nodes are nucleotides and edges represent chemical interactions. In this setting, we have biological evidence of the similarity between the edge types, as some chemical interactions are more similar than others. Machine learning on graphs have recently experienced a breakthrough with the introduction of Graph Neural Networks. This algorithm can be framed as a message passing algorithm between graph nodes over graph edges. These messages can depend on the edge type they are transmitted through, but no method currently constrains how a message is altered when the edge type changes. Motivated by the RNA use case, in this project we introduce a graph neural network layer which can leverage prior information about similarities between edges. We show that despite the theoretical appeal of including this similarity prior, the empirical performance is not enhanced on the tasks and datasets we include here.