4 papers
Locality Sensitive Hashing in Hyperbolic Space
Chengyuan Deng, Jie Gao, Kevin Lu +2
For a metric space , a family of locality sensitive hash functions is called sensitive if a randomly chosen function ha…
Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry
Chengyuan Deng, Jie Gao, Kevin Lu +2
The Johnson-Lindenstrauss (JL) lemma is a cornerstone of dimensionality reduction in Euclidean space, but its applicability to non-Euclidean data has remained limited. This paper e…
TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
Cheng Xin, Fan Xu, Xin Ding +2
Graph Neural Networks (GNNs) have shown remarkable success across various scientific fields, yet their adoption in critical decision-making is often hindered by a lack of interpret…
Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
Chengyuan Deng, Jie Gao, Kevin Lu +3
We introduce Non-Euclidean-MDS (Neuc-MDS), an extension of classical Multidimensional Scaling (MDS) that accommodates non-Euclidean and non-metric inputs. The main idea is to gener…