Symmetric Sparse Boolean Matrix Factorization and Applications

In this work, we study a variant of nonnegative matrix factorization where we wish to find a symmetric factorization of a given input matrix into a sparse, Boolean matrix. Formally speaking, given , we want to find such that is minimized among all for which each row is -sparse. This question turns out to be closely related to a number of questions like recovering a hypergraph from its line graph, as well as reconstruction attacks for private neural network training. As this problem is hard in the worst-case, we study a natural average-case variant that arises in the context of these reconstruction attacks: for a random Boolean matrix with -sparse rows, and the goal is to recover up to column permutation. Equivalently, this can be thought of as recovering a uniformly random -uniform hypergraph from its line graph. Our main result is a polynomial-time algorithm for this problem based on bootstrapping higher-order information about and then decomposing an appropriate tensor. The key ingredient in our analysis, which may be of independent interest, is to show that such a matrix has full column rank with high probability as soon as , which we do using tools from Littlewood-Offord theory and estimates for binary Krawtchouk polynomials.
View on arXiv