Problem
Research questions and friction points this paper is trying to address.
Recurrent Graph Neural Networks
Persistent Gaussian Perturbations
Node Separation
Finite-Time Analysis
Noncentral Chi-Square
Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian Perturbations
🤖 AI Summary
本文通过引入持久性高斯扰动，解决了递归图神经网络中节点表示在有限深度下保持区分性的问题，并提供了有限时间内的分析与保证。
📝 Abstract
Persistent Gaussian perturbations have been shown to prevent asymptotic oversmoothing in recurrent Graph Neural Networks (GNNs) by ensuring a positive stationary Dirichlet energy. However, this global energy bound does not guarantee that individual node representations remain distinct at finite depths. In this paper, we provide a complementary finite-time analysis of the same persistent-noise architecture. Let \(d\) denote the representation dimension and \(σ\) the noise standard deviation. We first prove an exact second-moment decomposition for the expected squared distance between any two node representations, yielding the universal lower bound \(2σ^2 d\) at every positive time step without contraction or stationarity assumptions. More precisely, conditional pairwise distances have a noncentral chi-square characterization: the noncentrality parameter is the deterministic message-passing separation normalized by \(2σ^2\). This yields dynamics-aware fixed-time and finite-horizon near-collision bounds that retain information discarded by the central worst-case analysis. The earlier central Gaussian bound is recovered as the worst-case zero-separation case. We additionally prove almost-sure pairwise noncollision, derive a uniform finite-horizon guarantee, and establish permutation equivariance in distribution for the stochastic dynamics and permutation-invariant graph outputs. Our results complement the asymptotic energy analysis of prior work and provide rigorous finite-time guarantees on node-level representation separation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
finite-time analysis
persistent Gaussian perturbations
noncentral chi-square distribution
node representation separation
permutation equivariance
🔎 Similar Papers
No similar papers found.
