Math 2.0

Resources / preprint

Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks EG1XXNSTXX

URIm2://res/EG1XXNSTXX
Kindpreprint
CreatorsMostafa Haghir Chehreghani
Date2026-07-30
Subjectsarxiv cs.LG, arxiv cs.AI, arxiv cs.IT, arxiv math.IT
Scopeborder

Expressions

e1: version, preprint

Date2026-07-30
IdsarXiv 2607.28185

Items in this resource

The mentions of the inventory that name this resource. Each name links to the card of its inventory row.

ItemKindWhereSource
3N4BQN5ZCDstatementproposition 3.2arxiv
Ergodicity of the projected Markov chainstatementtheorem 5.1arxiv
Projected Gaussian noisestatementlemma 3.1arxiv
Uniform boundedness of second momentsstatementlemma 5.5arxiv
83KJ918WA1statementcorollary 5.7arxiv
Escape from oversmoothing under contractive noisy recurrent dynamicsstatementtheorem 5.6arxiv
Contractive variance estimatestatementlemma 5.3arxiv
Dirichlet energydefinitiondefinition 3.1arxiv
Projected dynamics define a Markov chainstatementproposition 4.1arxiv
Escape from oversmoothingdefinitiondefinition 3.3arxiv
KZK62V2GD0statementlemma 3.3arxiv
Exact stationary second-moment identitystatementproposition 5.2arxiv
Oversmoothingdefinitiondefinition 3.2arxiv
Positive lower bound on the stationary variancestatementtheorem 5.4arxiv

Catalogue records