DeepWalk: Online Learning of Social Representations, Bryan Perozzi, Rami Al-Rfou, Steven Skiena, 2014KDD '14: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM)DOI: 10.1145/2623330.2623732 - This foundational paper introduces DeepWalk, a pioneering random walk-based method for learning node embeddings by treating random walks as "sentences" and applying Word2Vec-like techniques.
node2vec: Scalable Feature Learning for Networks, Aditya Grover, Jure Leskovec, 2016KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM)DOI: 10.1145/2939672.2939754 - This paper extends DeepWalk by proposing node2vec, an algorithm that learns node embeddings through biased random walks, allowing it to capture a flexible balance between BFS-like and DFS-like neighborhood exploration.
Graph Neural Networks: A Review of Methods and Applications, Jie Zhou, Ganqu Cui, Zhengyan Zhang, Cheng Yang, Zhiyuan Liu, Maosong Sun, and Liqiang Nie, 2021AI Open, Vol. 1DOI: 10.1016/j.aiopen.2021.01.001 - A comprehensive survey providing an overview of various Graph Neural Network (GNN) models, their applications, and future research directions, relevant for understanding this powerful family of graph embedding techniques.