An Unsupervised Framework for Comparing Graph Embeddings The goal of many machine learning applications is to make predictions or discover new patterns using graph-structured data as feature information. In order to extract useful structural information from graphs, one might want

Conditions for perfect matchings in random sparse bipartite graphs Given a uniformly random sparse matrix A, with specified number of nonzero entries in columns and rows, we determine when A has full row rank over a finite field. As a