Towards Distributed Graph Representation Learning

Distributed graph representation learning refers to the process of learning graph data representation in a distributed computing environment. In the process of distributed graph representation learning, nodes need to exchange data frequently, making data transmission crucial in this context. The content of data transmission, including plaintext data, ciphertext data, and model parameters, affects the performance, computational and communication costs, and privacy protection of distributed graph representation learning. However, there is currently a lack of comprehensive investigations into distributed graph representation learning. This paper fills this gap by conducting a detailed study on distributed graph representation learning and summarizing various methods for transmitting different types of content. We review the applications and evaluation methods of distributed graph representation learning and, through an analysis of the strengths and limitations of existing research, provide insights into the future development directions of distributed graph representation learning.