LEAP: Local ECT-Based Learnable Positional Encodings for Graphs

ICLR 2026 Conference Submission13677 Authors

Keywords: Topology, Euler Characteristic Transform, Graph Neural Networks, Topological Data Analysis, TDA, Topological Deep Learning

TL;DR: Local ECT-Based Learnable Positional Encodings for Graphs

Abstract: Graph neural networks (GNNs) largely rely on the message-passing paradigm, where nodes iteratively aggregate information from their neighbors. Yet, standard message passing neural networks (MPNNs) face well-documented theoretical and practical limitations. Graph positional encoding (PE) has emerged as a promising direction to address these limitations. The Euler Characteristic Transform (ECT) is an efficiently computable geometric–topological invariant that characterizes shapes and graphs. In this work, we combine the differentiable approximation of the ECT (DECT) and its local variant ($\ell$-ECT) to propose LEAP, a new end-to-end trainable local structural PE for graphs. We evaluate our approach on multiple real-world datasets as well as on a synthetic task designed to test its ability to extract topological features. Our results underline the potential of LEAP-based encodings as a powerful component for graph representation learning pipelines.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 13677