arXiv:2604.24293 · v2

Mitigating Global Feature Collapse in Graph ODEs via Hysteretic Topology Evolution

首次提交 2026-04-27 18:27

版本更新 2026-11-09 22:19

雷达观测 2026-11-10 15:22

摘要

Graph neural ordinary differential equations provide continuous-time propagation on graphs, but their long-time behavior is largely determined by the asymptotic structure of the mixing operator. We show that diffusion-style Graph ODEs with positive irreducible mixing face a \emph{monostability trap}, where node features converge to a rank-one consensus subspace. This reveals a structural limitation of positive diffusion-style continuous graph propagation: within this consensus class, exact long-time avoidance requires changing the effective support; otherwise, smooth suppression should be interpreted as finite-horizon or metastable mitigation. We address this by introducing a \emph{hysteretic mechanism} for topology evolution, where candidate edges carry latent bistable potentials in a double-well landscape. A node-feature-conditioned force field evolves these potentials, and a smooth sigmoid gate converts them into differentiable propagation weights. We prove global consensus under the stated mixing assumptions and block-wise consensus under idealised support separation. For consensus-form dynamics, we further establish a finite-horizon perturbation bound under small cross-block leakage, and empirically evaluate the resulting nonlinear HGODE on node- and graph-level benchmarks.

作者备注：Accepted by NeurIPS 2026