Can NetGAN be improved on short random walks?
arXiv:1905.05298
Abstract
Graphs are useful structures that can model several important real-world problems. Recently, learning graphs have drawn considerable attention, leading to the proposal of new methods for learning these data structures. One of these studies produced NetGAN, a new approach for generating graphs via random walks. Although NetGAN has shown promising results in terms of accuracy in the tasks of generating graphs and link prediction, the choice of vertices from which it starts random walks can lead to inconsistent and highly variable results, especially when the length of walks is short. As an alternative to random starting, this study aims to establish a new method for initializing random walks from a set of dense vertices. We purpose estimating the importance of a node based on the inverse of its influence over the whole vertices of its neighborhood through random walks of different sizes. The proposed method manages to achieve significantly better accuracy, less variance and lesser outliers.
arXiv comment6 pages, 6 figures, 1 table, 10 equations, 22 citations Paper was submited to BRACIS conferece 2019
References in corpus (11)
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Graph Neural Networks: A Review of Methods and Applications
- NIPS 2016 Tutorial: Generative Adversarial Networks
- Learning Combinatorial Optimization Algorithms over Graphs
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Interaction Networks for Learning about Objects, Relations and Physics
- Graph networks as learnable physics engines for inference and control
- NetGAN: Generating Graphs via Random Walks
- Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach