L-STEP learns time-evolving positional encodings for graph nodes via a learnable spectral filter and predicts links with MLPs only, matching or beating attention-based baselines on 13 temporal datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learnable Spatial-Temporal Positional Encoding for Link Prediction
L-STEP learns time-evolving positional encodings for graph nodes via a learnable spectral filter and predicts links with MLPs only, matching or beating attention-based baselines on 13 temporal datasets.