Beyond Observed Connections : Link Injection
This addresses the challenge of incomplete graph data for researchers and practitioners in graph machine learning, though it appears incremental as it builds on existing differentiable models.
The paper tackles the problem of graph machine learning models being limited to observed connections in input data by proposing link injection, a method that helps models discover and exploit unseen connections for tasks like node classification and link prediction, resulting in improved performance across various state-of-the-art models.
In this paper, we proposed the \textit{link injection}, a novel method that helps any differentiable graph machine learning models to go beyond observed connections from the input data in an end-to-end learning fashion. It finds out (weak) connections in favor of the current task that is not present in the input data via a parametric link injection layer. We evaluate our method on both node classification and link prediction tasks using a series of state-of-the-art graph convolution networks. Results show that the link injection helps a variety of models to achieve better performances on both applications. Further empirical analysis shows a great potential of this method in efficiently exploiting unseen connections from the injected links.