Hyperbolic CNNs outperform Euclidean CNNs on 37 of 42 genome classification benchmarks and beat several large DNA language models on 7 GUE tasks using orders of magnitude fewer parameters.
Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Hyperbolic space naturally encodes hierarchical structures such as phylogenies (binary trees), where inward-bending geodesics reflect paths through least common ancestors, and the exponential growth of neighborhoods mirrors the super-exponential scaling of topologies. This scaling challenge limits the efficiency of Euclidean-based approximate inference methods. Motivated by the geometric connections between trees and hyperbolic space, we develop novel hyperbolic extensions of two sequential search algorithms: Combinatorial and Nested Combinatorial Sequential Monte Carlo (\textsc{Csmc} and \textsc{Ncsmc}). Our approach introduces consistent and unbiased estimators, along with variational inference methods (\textsc{H-Vcsmc} and \textsc{H-Vncsmc}), which outperform their Euclidean counterparts. Empirical results demonstrate improved speed, scalability and performance in high-dimensional phylogenetic inference tasks.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hyperbolic Genome Embeddings
Hyperbolic CNNs outperform Euclidean CNNs on 37 of 42 genome classification benchmarks and beat several large DNA language models on 7 GUE tasks using orders of magnitude fewer parameters.