Graph Representation Learning

Abstract

Continuous graph neural models based on differential equations have expanded the architecture of graph neural networks (GNNs). Due to the connection between graph diffusion and message passing, diffusion-based models have been widely studied. However, diffusion naturally drives the system towards an equilibrium state, leading to issues like over-smoothing. To this end, we propose GRADE inspired by GRaph Aggregation-Diffusion Equations, which includes the delicate balance between nonlinear diffusion and aggregation induced by interaction potentials. The node representations obtained through aggregationdiffusion equations exhibit metastability, indicating that features can aggregate into multiple clusters. In addition, the dynamics within these clusters can persist for long time periods, offering the potential to alleviate over-smoothing effects. This nonlinear diffusion in our model generalizes existing diffusion-based models and establishes a connection with classical GNNs. We prove that GRADE achieves competitive performance across various benchmarks and alleviates the over-smoothing issue in GNNs evidenced by the enhanced Dirichlet energy.

Model for Quantitative Estimation of Functionality Influence on the Final Value of a Software Product

“…The first crucial aspect to consider is the VOLUME 4, 2023 best way to represent (and encode) existing domain knowledge into a form suitable to be integrated into quantitative processes [6], [7]. Graphs are a data structure capable of encoding complex knowledge and relationships into a form suitable for quantitative approaches [8]- [10]. Consequently, the quantitative method that is presented in this paper uses graphs to represent the structure of the software product by describing the relationship between the requirements, functionalities, and end value.…”