HAT-GAE: Self-Supervised Graph Auto-encoders with Hierarchical Adaptive Masking and Trainable Corruption
This addresses the challenge of learning representations from non-Euclidean graph data for applications in domains like social networks or bioinformatics, but appears incremental as it builds on existing auto-encoder frameworks.
The paper tackled the problem of limited performance in self-supervised auto-encoders for graph representation learning by proposing HAT-GAE, which incorporates hierarchical adaptive masking and trainable corruption, and demonstrated superiority over state-of-the-art models on ten benchmark datasets.
Self-supervised auto-encoders have emerged as a successful framework for representation learning in computer vision and natural language processing in recent years, However, their application to graph data has been met with limited performance due to the non-Euclidean and complex structure of graphs in comparison to images or text, as well as the limitations of conventional auto-encoder architectures. In this paper, we investigate factors impacting the performance of auto-encoders on graph data and propose a novel auto-encoder model for graph representation learning. Our model incorporates a hierarchical adaptive masking mechanism to incrementally increase the difficulty of training in order to mimic the process of human cognitive learning, and a trainable corruption scheme to enhance the robustness of learned representations. Through extensive experimentation on ten benchmark datasets, we demonstrate the superiority of our proposed method over state-of-the-art graph representation learning models.