arXiv subjects

Jinye Yang

Publications and source records attributed to Jinye Yang.

4 recordsLinked to original sources

arXiv2024

Faithful Density-Peaks Clustering via Matrix Computations on MPI Parallelization System

Density peaks clustering (DP) has the ability of detecting clusters of arbitrary shape and clustering non-Euclidean space data, but its quadratic complexity in both computing and storage makes it difficult to scale for big data. Various approaches have been proposed in this regard, including MapReduce based distribution computing, multi-core parallelism, presentation transformation (e.g., kd-tree, Z-value), granular computing, and so forth. However, most of these existing methods face two limitations. One is their target datasets are mostly constrained to be in Euclidian space, the other is they emphasize only on local neighbors while ignoring global data distribution due to restriction to cut-off kernel when computing density. To address the two issues, we present a faithful and parallel DP method that makes use of two types of vector-like distance matrices and an inverse leading-node-finding policy. The method is implemented on a message passing interface (MPI) system. Extensive experiments showed that our method is capable of clustering non-Euclidean data such as in community detection, while outperforming the state-of-the-art counterpart methods in accuracy when clustering large Euclidean data. Our code is publicly available at https://github.com/alanxuji/FaithPDP.

cs.LG↗

arXiv2023

Long-Tailed Classification Based on Coarse-Grained Leading Forest and Multi-Center Loss

Long-tailed (LT) classification is an unavoidable and challenging problem in the real world. Most existing long-tailed classification methods focus only on solving the class-wise imbalance while ignoring the attribute-wise imbalance. The deviation of a classification model is caused by both class-wise and attribute-wise imbalance. Due to the fact that attributes are implicit in most datasets and the combination of attributes is complex, attribute-wise imbalance is more difficult to handle. For this purpose, we proposed a novel long-tailed classification framework, aiming to build a multi-granularity classification model by means of invariant feature learning. This method first unsupervisedly constructs Coarse-Grained forest (CLF) to better characterize the distribution of attributes within a class. Depending on the distribution of attributes, one can customize suitable sampling strategies to construct different imbalanced datasets. We then introduce multi-center loss (MCL) that aims to gradually eliminate confusing attributes during feature learning process. The proposed framework does not necessarily couple to a specific LT classification model structure and can be integrated with any existing LT method as an independent component. Extensive experiments show that our approach achieves state-of-the-art performance on both existing benchmarks ImageNet-GLT and MSCOCO-GLT and can improve the performance of existing LT methods. Our codes are available on GitHub: \url{https://github.com/jinyery/cognisance}

cs.CV↗

arXiv2018

Iron Line Spectroscopy of Black Holes in Vector-Tensor Galileons Modified Gravity

Recently, a rotating black hole solution was found in Vector-Tensor Galileons modified gravity that has some significant differences from the Kerr black hole solution. We study the iron line shape that is part of the reflection spectrum of accretion disks around black holes in this new black hole solution. We simulate and compare the iron lines of this solution with those of the Kerr solution to see if the technique of iron line spectroscopy can be used as a tool to test Vector-Tensor Galileons modified gravity. Our analysis shows that current X-ray facilities can, in principle, be used to test and place constraints on Vector-Tensor Galileons modified gravity in the strong coupling and ultraspinning regimes.

gr-qc↗

arXiv2016

Observational properties of rigidly rotating dust configurations

We study the observational properties of a class of exact solutions of Einstein's field equations describing stationary, axially symmetric, rigidly rotating dust (i.e. non interacting particles). We ask the question whether such solutions can describe astrophysical rotating dark matter clouds near the center of galaxies and we probe the possibility that they may constitute an alternative to supermassive black holes at the center of galaxies. We show that light emission from accretion disks made of ordinary baryonic matter in this space-time has several differences with respect to the emission of light from similar accretion disks around black holes. The shape of the iron K$\alpha$ line in the reflection spectrum of accretion disks can potentially distinguish this class of solution from the Kerr metric, but this may not be possible with current X-ray missions.

gr-qc↗