Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
This work addresses graph representation learning for compute vision tasks, offering incremental improvements by handling inherent data distributions and noises to reduce over-fitting.
The paper tackles the problem of graph representation learning by proposing DBGAN, which estimates prior distributions in a structure-aware way and uses bidirectional adversarial learning to balance consistency, resulting in improved trade-off between representation and robustness and dimension efficiency across various tasks.
Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks. However, most existing algorithms ignore the existence of inherent data distribution and even noises. This may significantly increase the phenomenon of over-fitting and deteriorate the testing accuracy. In this paper, we propose a Distribution-induced Bidirectional Generative Adversarial Network (named DBGAN) for graph representation learning. Instead of the widely used normal distribution assumption, the prior distribution of latent representation in our DBGAN is estimated in a structure-aware way, which implicitly bridges the graph and feature spaces by prototype learning. Thus discriminative and robust representations are generated for all nodes. Furthermore, to improve their generalization ability while preserving representation ability, the sample-level and distribution-level consistency is well balanced via a bidirectional adversarial learning framework. An extensive group of experiments are then carefully designed and presented, demonstrating that our DBGAN obtains remarkably more favorable trade-off between representation and robustness, and meanwhile is dimension-efficient, over currently available alternatives in various tasks.