SyncAI.news, a Varaisys broadcasting
Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagation
PX

Ping Xiong, Shanglin Li, Yi Ding, Thomas Schnake, Shinichi Nakajima

· 1 min read

ResearcharXiv cs.LG

Explaining Hyperbolic Neural Networks via Geometry-Aware Relevance Propagation

arXiv:2609.35128v1 Announce Type: new Abstract: 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 relevance entirely to the signal branch. The rule conserves relevance, is invariant to equivalent radial factorizations, and satisfies zero-curvature consistency, yielding GRI for a specified Poincar\'e-Lorentz logarithmic-map construction. In contrast, a conservative LRP-half baseline can violate both consistency criteria. Experiments on hyperbolic MNIST, sEEG, and CIFAR-10 classifiers assess attribution fidelity, qualitative explanations, and runtime. LRP-radial-all achieves competitive attribution fidelity across datasets with runtime comparable to Gradient$\times$Input and substantially lower than Integrated Gradients. These findings motivate geometry-aware propagation rules that distinguish relevance conservation from consistency across equivalent computations.

Original source

This story was published by arXiv cs.LG and written by Ping Xiong, Shanglin Li, Yi Ding, Thomas Schnake, Shinichi Nakajima. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News