English

Asymptotics of $\ell_2$ Regularized Network Embeddings

Machine Learning 2022-12-20 v3 Machine Learning Statistics Theory Statistics Theory

Abstract

A common approach to solving prediction tasks on large networks, such as node classification or link prediction, begin by learning a Euclidean embedding of the nodes of the network, from which traditional machine learning methods can then be applied. This includes methods such as DeepWalk and node2vec, which learn embeddings by optimizing stochastic losses formed over subsamples of the graph at each iteration of stochastic gradient descent. In this paper, we study the effects of adding an 2\ell_2 penalty of the embedding vectors to the training loss of these types of methods. We prove that, under some exchangeability assumptions on the graph, this asymptotically leads to learning a graphon with a nuclear-norm-type penalty, and give guarantees for the asymptotic distribution of the learned embedding vectors. In particular, the exact form of the penalty depends on the choice of subsampling method used as part of stochastic gradient descent. We also illustrate empirically that concatenating node covariates to 2\ell_2 regularized node2vec embeddings leads to comparable, when not superior, performance to methods which incorporate node covariates and the network structure in a non-linear manner.

Keywords

Cite

@article{arxiv.2201.01689,
  title  = {Asymptotics of $\ell_2$ Regularized Network Embeddings},
  author = {Andrew Davison},
  journal= {arXiv preprint arXiv:2201.01689},
  year   = {2022}
}

Comments

Accepted in Neural Information Processing Systems 2022. 44 pages, 2 figures, 2 tables

R2 v1 2026-06-24T08:41:03.082Z