Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces

arXiv CS · · 2 min read · Engineering & Technology

Read research and analysis on Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces published by ICANEWS, a global research journal for emerging researchers.

Key Takeaways

  • Proposed PEs are gauge-invariant by construction as a matrix function of the operator.
  • Computation is achieved in a Hermitian block Krylov subspace using only sparse matrix-vector products.
  • $k = O(\log(1/\varepsilon))$ block steps suffice uniformly over heat-resolvent response families.
  • Low-dimensional, structured families generalize where free per-eigenvalue weights overfit.
  • Magnetic Krylov PEs converge to the exact-eigendecomposition oracle on directed SBMs, outperforming direction-blind PEs.
  • Yields gauge-invariant pairwise features with $1/\sqrt{s}$ Monte-Carlo error.
  • Improves heterophilous benchmarks over no-PE and polynomial baselines in the undirected $q{=}0$ case.

Why This Matters

The development of these learnable spectral PEs provides a method to address computational complexity and gauge ambiguity in processing directed graphs. This approach offers a structured means to generate rich features from graph topology, which can improve performance in tasks on both directed and certain undirected graphs.

Overview

This work proposes learnable spectral positional encodings (PEs) designed for directed graphs. The method addresses two challenges associated with magnetic Laplacians in directed graphs: the $O(n^3)$ computational complexity for Hermitian eigendecomposition per potential and the unitary gauge ambiguity of complex eigenvectors. The proposed PEs are formulated as a matrix function $h_\theta(A_q)\,R$, where $A_q$ is a normalized magnetic operator, $h_\theta$ represents a learnable scalar spectral response, and $R$ is a block of random probes. This formulation inherently ensures gauge-invariance. The computational approach leverages Hermitian block Krylov subspaces, relying solely on sparse matrix-vector products.

Research Context

Spectral positional encodings for directed graphs encounter specific obstacles. Magnetic Laplacians, which are relevant for directed graphs, necessitate a Hermitian eigendecomposition that scales with $O(n^3)$ computational cost for each potential value. Furthermore, the complex eigenvectors derived from these Laplacians are defined only up to a unitary gauge, a factor that prior research has addressed through the use of basis-invariant architectural designs. The current work aims to provide an alternative solution to these challenges.

Approach

The proposed spectral PEs are defined by the form $h_\theta(A_q)\,R$. In this formulation, $A_q$ functions as a normalized magnetic operator. The term $h_\theta$ denotes a learnable scalar spectral response, while $R$ represents a block of random probes. A key aspect of this approach is that the PE is conceptualized as a matrix function of the operator $A_q$. This design choice ensures gauge-invariance by construction. The computation of this matrix function is performed within a Hermitian block Krylov subspace. This computation exclusively utilizes sparse matrix-vector products. The researchers prove that $k = O(\log(1/\varepsilon))$ block steps are sufficient, a uniformity that holds across families of heat-resolvent response functions. A covering-number argument is also provided to explain why low-dimensional, structured families demonstrate generalizability, contrasting with free per-eigenvalue weights that tend to overfit.

Findings

  • The proposed PE formulation, $h_\theta(A_q)\,R$, maintains gauge-invariance due to its definition as a matrix function of the operator.
  • The computation in a Hermitian block Krylov subspace relies exclusively on sparse matrix-vector products.
  • It was proven that $k = O(\log(1/\varepsilon))$ block steps are sufficient universally for heat-resolvent response families.
  • A covering-number argument indicates that low-dimensional, structured families generalize effectively, while free per-eigenvalue weights are prone to overfitting.
  • On a directed Stochastic Block Model (SBM) where the symmetrization is uninformative by design, direction-blind PEs perform at chance levels. In contrast, magnetic Krylov PEs converge to the exact-eigendecomposition oracle as the depth increases.
  • The same probes used in the PE formulation yield gauge-invariant pairwise features with a Monte-Carlo error of $1/\sqrt{s}$.
  • For the undirected case where $q{=}0$, the method shows improvements on heterophilous benchmarks when compared to no-PE and polynomial baselines.

Research Information

Institution
arXiv CS
Original Study
View Publication
Source
arXiv CS

About ICANEWS

ICANEWS is a global research journal for emerging researchers, publishing student and emerging researcher work across all fields.