paper
Understanding Truncated Positional Encodings for Graph Neural Networks
paperactiveprovisional
understanding-truncated-positional-encodings-for-graph-neural-networks-75acaf68·1 events·first seen 5d agoAliases: Understanding Truncated Positional Encodings for Graph Neural Networks
More like this (12)
Graph Neural Network EncoderGraph Neural NetworksPositional EncodingGraph TransformerTopological Neural OperatorsGraph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous GraphsE(3) equivariant graph neural networkSparse AutoencodersSurface-Anchored Position EmbeddingGraph Structure LearningNatural Language Autoencodersq0: Primitives for Hyper-Epoch Pretraining
Recent events (1)
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.