No AI summary available for this article.
Why It Matters
Hyperbolic neural networks introduce geometric operations that require explicit treatment in relevance propagation.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Hyperbolic neural networks introduce geometric operations that require explicit treatment in relevance propagation. Equivalent geometric realizations can produce different feature attributions, even when local relevance is conserved. We study this problem through Geometric Representation Invariance (GRI), a specialization of Implementation Invariance, and zero-curvature consistency, which requires identity relevance propagation when a geometric module approaches the identity. We propose LRP-radial-all for origin-centered radial modules, treating geometric scaling as modulation and assigning re...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.35128v1 · Indexed about 1 hour ago