GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs
This addresses the problem of creating generalizable representations for downstream tasks in domains like social networks or citation graphs, but it appears incremental as it builds on existing methods.
The paper tackles self-supervised representation learning on text-attributed graphs by proposing GRENADE, a model that combines pre-trained language models and graph neural networks with specialized self-supervised algorithms, achieving superiority over state-of-the-art methods in experiments.
Self-supervised representation learning on text-attributed graphs, which aims to create expressive and generalizable representations for various downstream tasks, has received increasing research attention lately. However, existing methods either struggle to capture the full extent of structural context information or rely on task-specific training labels, which largely hampers their effectiveness and generalizability in practice. To solve the problem of self-supervised representation learning on text-attributed graphs, we develop a novel Graph-Centric Language model -- GRENADE. Specifically, GRENADE exploits the synergistic effect of both pre-trained language model and graph neural network by optimizing with two specialized self-supervised learning algorithms: graph-centric contrastive learning and graph-centric knowledge alignment. The proposed graph-centric self-supervised learning algorithms effectively help GRENADE to capture informative textual semantics as well as structural context information on text-attributed graphs. Through extensive experiments, GRENADE shows its superiority over state-of-the-art methods. Implementation is available at \url{https://github.com/bigheiniu/GRENADE}.