TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows
Eliasof, Moshe, Haber, Eldad, Schönlieb, Carola-Bibiane
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Aug-8-2025
- Country:
- North America (0.46)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.28)
- Genre:
- Research Report (1.00)
- Industry:
- Technology: