English

TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows

Machine Learning 2025-08-08 v1

Abstract

We introduce TANGO -- a dynamical systems inspired framework for graph representation learning that governs node feature evolution through a learned energy landscape and its associated descent dynamics. At the core of our approach is a learnable Lyapunov function over node embeddings, whose gradient defines an energy-reducing direction that guarantees convergence and stability. To enhance flexibility while preserving the benefits of energy-based dynamics, we incorporate a novel tangential component, learned via message passing, that evolves features while maintaining the energy value. This decomposition into orthogonal flows of energy gradient descent and tangential evolution yields a flexible form of graph dynamics, and enables effective signal propagation even in flat or ill-conditioned energy regions, that often appear in graph learning. Our method mitigates oversquashing and is compatible with different graph neural network backbones. Empirically, TANGO achieves strong performance across a diverse set of node and graph classification and regression benchmarks, demonstrating the effectiveness of jointly learned energy functions and tangential flows for graph neural networks.

Keywords

Cite

@article{arxiv.2508.05070,
  title  = {TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows},
  author = {Moshe Eliasof and Eldad Haber and Carola-Bibiane Schönlieb},
  journal= {arXiv preprint arXiv:2508.05070},
  year   = {2025}
}
R2 v1 2026-07-01T04:38:30.184Z