Almanac
paper

Understanding Truncated Positional Encodings for Graph Neural Networks

paperactiveprovisionalunderstanding-truncated-positional-encodings-for-graph-neural-networks-75acaf68·1 events·first seen 5d ago

Aliases: Understanding Truncated Positional Encodings for Graph Neural Networks

More like this (12)

Recent events (1)

4arXiv · cs.LG·5d ago·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.