AI RESEARCH

node2vec or triangle-biased random walks: stationarity, regularity & recurrence

arXiv CS.LG

ArXi:2604.13681v1 Announce Type: cross The node2vec random walk is a non-Markovian random walk on the vertex set of a graph, widely used for network embedding and exploration. This random walk model is defined in terms of three parameters which control the probability of, respectively, backtracking moves, moves within triangles, and moves to the remaining neighboring nodes. From a mathematical standpoint, the node2vec random walk is a nontrivial generalization of the non-backtracking random walk and thus belongs to the class of second-order Marko chains.