activity
20052024
most citedAre All Losses Created Equal: A Neural Collapse Perspective

8 citations · 13 across the 12 of their papers we have counts for

collaborators

12 papers

cs.HC2024

Analysis of the Causes of Car Accidents in the United States of America in 2023: Gauge People Understanding of Data Visualisation

Hamoud Alhazmi, Marcelo Morales, Jiachen Jiang +2

This paper presents a comprehensive examination of interactive data visualization tools and their efficacy in the context of United States car accident data for the year 2023. We d…

math.CO2024

The classification of two-distance transitive dihedrants

Jun-Jie Huang, Yan-Quan Feng, Jin-Xin Zhou +1

A vertex transitive graph is said to be -distance transitive if for each vertex , the group of automorphisms of fixing the vertex acts transitively on the set of…

math.GR2023

Quasiprimitive groups with a biregular dihedral subgroup,and arc-transitive bidihedrants

Jiangmin Pan, Fu-Gang Yin, Jin-Xin Zhou

A semiregular permutation group on a set $\Ome$ is called {\em bi-regular} if it has two orbits. A classification is given of quasiprimitive permutation groups with a biregular dih…

math.CO2023

Using mixed dihedral groups to construct normal Cayley graphs, and a new bipartite -arc-transitive graph which is not a Cayley graph

Daniel R. Hawtin, Cheryl E. Praeger, Jin-Xin Zhou

A \emph{mixed dihedral group} is a group with two disjoint subgroups and , each elementary abelian of order , such that is generated by , and $H/H'\con…

math.CO2023

A family of -groups and an associated family of semisymmetric, locally -arc-transitive graphs

Daniel R. Hawtin, Jin-Xin Zhou, Cheryl E. Praeger

A mixed dihedral group is a group with two disjoint subgroups and , each elementary abelian of order , such that is generated by , and $H/H'\cong X\tim…

cs.LG20228 cited

Are All Losses Created Equal: A Neural Collapse Perspective

Jinxin Zhou, Chong You, Xiao Li +4

While cross entropy (CE) is the most commonly used loss to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empiric…