Learnable spectral positional encodings for directed graphs are computed as gauge-invariant matrix functions of the magnetic operator via block Krylov subspaces, achieving O(log(1/ε)) approximation with sparse matrix-vector products only.
Proceedings of the Twenty-Ninth Annual ACM-SIAM Symposium on Discrete Algorithms , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gauge-Invariant Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces
Learnable spectral positional encodings for directed graphs are computed as gauge-invariant matrix functions of the magnetic operator via block Krylov subspaces, achieving O(log(1/ε)) approximation with sparse matrix-vector products only.