Papers › Asymptotics of ℓ₂ Regularized Network Embeddings

Asymptotics of ℓ₂ Regularized Network Embeddings

5 Jan 2022arXiv:2201.01689archive 2025-07-28

Andrew Davison

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 ℓ₂ 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 ℓ₂ 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.

PaperPDFCode

Code

aday651/embed-reg officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Link PredictionNode Classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DeepWalknode2vec

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections