Just a practice of frozen pre-train [1] on graph-structured data with GraphSaint sampler [2]
[1] Lu, K., Grover, A., Abbeel, P., & Mordatch, I. (2022, June). Frozen pretrained transformers as universal computation engines. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 36, No. 7, pp. 7628-7636).
[2] Zeng, H., Zhou, H., Srivastava, A., Kannan, R., & Prasanna, V. (2019). Graphsaint: Graph sampling based inductive learning method. arXiv preprint arXiv:1907.04931.