Entity · paper

Understanding Truncated Positional Encodings for Graph Neural Networks

paperactiveunderstanding-truncated-positional-encodings-for-graph-neural-networks-75acaf68·1 events·first seen Jun 12, 2026

Aliases: Understanding Truncated Positional Encodings for Graph Neural Networks

More like this (12)

Graph Neural Network Encoder Graph Neural Networks Linear representations of grammaticality in neural language models Positional Encoding Graph Transformer Topological Neural Operators Anti-Periodic Positional Encoding: Möbius Boundary Conditions Make In-Context Retrieval Reliable Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs E(3) equivariant graph neural network How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization Sparse Autoencoders Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects

Recent events (1)

4arXiv · cs.LG·Jun 12, 2026·source ↗

Theoretical analysis of truncated positional encodings for graph neural networks

A new arXiv paper initiates a formal study of truncated positional encodings (PEs) for graph neural networks, showing that truncation breaks the theoretical equivalence between spectral and walk-based PE families. Key findings include that truncated spectral PEs lose their advantage over the 1-WL expressivity test, and that k-harmonic distances differ meaningfully from other closely related truncated spectral PEs. Experiments on real-world datasets suggest mixing truncated PE families outperforms any single family.

Evaluation and Benchmarking Understanding Truncated Positional Encodings for Graph Neural Networks