Group-Equivariant Poincaré Convolutional Networks
While recent methods like that of the Poincaré ResNet have demonstrated the ability to learning visual representations directly in hyperbolic space, their optimisation remains a challenge, primarily due to the parameter redundancy of learning distinct orientation filters. In addition, hyperbolic learning exhibits distinct computational overheads that limit their wide use, where efforts to improve their efficiency via optimisation have seen good success, there has been limited exploration into structural priors that enable stronger sample efficiency at training. To address this, we propose Equivariant Poincaré ResNets, combining hyperbolic geometry with discrete symmetry groups ($C_4$ and $D_4$). We identify critical roadblocks in applying Euclidean equivariance to hyperbolic space and propose geometrically safe tensor reshaping, left-regular permutations for hyperbolic group convolutions, and joint-orientation Poincaré Midpoint Batch normalisation. Empirical evaluations show that embedding equivariance significantly improves the sample efficiency during training which in-turn accelerates convergence while respecting the boundary constraints of the Poincaré ball and retaining spatial group equivariance.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Clifford-Steerable Convolutional Neural Networks
We present Clifford-Steerable Convolutional Neural Networks (CS-CNNs), a novel class of $\mathrm{E}(p, q)$-equivariant CNNs. CS-CNNs process multivector fields on pseudo-Euclidean spaces $\mathbb{R}^{p,q}$. They cover, f…
Exploiting Equivariance in the Design of Tracking Controllers for Euler-Poincare Systems on Matrix Lie Groups
The trajectory tracking problem is a fundamental control task in the study of mechanical systems. A key construction in tracking control is the error or difference between an actual and desired trajectory. This construct…
Learning Irreducible Representations of Noncommutative Lie Groups
Recent work has constructed neural networks that are equivariant to continuous symmetry groups such as 2D and 3D rotations. This is accomplished using explicit group representations to derive the equivariant kernels and …
ObjectObject TrackingComputing Representations for Lie Algebraic Networks
Recent work has constructed neural networks that are equivariant to continuous symmetry groups such as 2D and 3D rotations. This is accomplished using explicit Lie group representations to derive the equivariant kernels …
Object TrackingScalars are universal: Equivariant machine learning, structured like classical physics
There has been enormous progress in the last few years in designing neural networks that respect the fundamental symmetries and coordinate freedoms of physical law. Some of these frameworks make use of irreducible repres…
BIG-bench Machine LearningTranslation