Higher-Order Positional Encodings for Graph Representation Learning

arXiv:2610.01903 · cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Code: https://github.com/ahoysal/lifted-pses

Terminology

• Representation Learning — 1× in this paper · explained in 2 episodes

Sources

• Architectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural Networks
• HOPSE: Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations
• Topological Deep Learning: Going Beyond Graph Data
• Attending to Topological Spaces: The Cellular Transformer

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks