Research
M-Fibration Theory with Applications to Neural Network Compression
arXiv:2608.25598v1 Announce Type: new Abstract: The purpose of this paper is to provide a general, comprehensive, theoretical framework that allows one to deal with fibrations on graphs labelled on a
arXiv:2608.25598v1 Announce Type: new Abstract: The purpose of this paper is to provide a general, comprehensive, theoretical framework that allows one to deal with fibrations on graphs labelled on a commutative monoid. This is a genuine extension of the theory of graph fibrations (as introduced in "Fibrations of Graphs" [Discrete Math., vol. 243, pp. 21-66, 2002]), that makes it possible to deal with weighted graphs, and also graphs labelled with other algebraic structures. The derived theory also lends itself naturally to consider approximate fibrations. As an example, we show how this framework can be applied to the compression of arbitrary neural networks (including CNNs), providing a strong theoretical underpinning to the recent results in "The role of fibration symmetries in geometric deep learning" [Proc. Natl. Acad. Sci. USA, vol. 123, no. 4, p. e2416552123, 2026]
Related
- A General Framework for Learning Algebraic Properties from Cayley Graphs using Graph Neural Networks
- Post-Training Neural Network Pruning using Graph Curvature
- Multi-stage neural operator learning with application for convolutions
Source: arXiv cs.LG | 2026-08-27