Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Disentangling Granularity: An Implicit Inductive Bias in Factorized VAEs
Zihao Chen, Yu Xiang, Wenyong Wang
Despite the success in learning semantically meaningful, unsupervised disentangled representations, variational autoencoders (VAEs) and their variants face a fundamental theoretica…
cs.LG2025
IIKL: Isometric Immersion Kernel Learning with Riemannian Manifold for Geometric Preservation
Zihao Chen, Wenyong Wang, Jiachen Yang +1
Geometric representation learning in preserving the intrinsic geometric and topological properties for discrete non-Euclidean data is crucial in scientific applications. Previous r…