no code implementations • 14 Feb 2021 • Urmish Thakker, Paul N. Whatmough, ZhiGang Liu, Matthew Mattina, Jesse Beu
Additionally, results with doped kronecker product matrices demonstrate state-of-the-art accuracy at large compression factors (10 - 25x) across 4 natural language processing applications with minor loss in accuracy.
no code implementations • journal 2019 • ZhiGang Liu, Dongyu Li, Shuzhi Sam Ge, Feng Tian
It concatenates the features of the different layers into a fused feature map to provide sufficient information for small traffic sign detection.
no code implementations • IEEE Transactions on Services Computing 2021 • Xin Luo, Yue Zhou, ZhiGang Liu, Lun Hu, Mengchu Zhou
A non-negative latent factor (NLF) model with a single latent factor-dependent, non-negative and multiplicative update (SLF-NMU) algorithm is frequently adopted to extract useful knowledge from non-negative data represented by high-dimensional and sparse (HiDS) matrices arising from various service applications.
no code implementations • 8 Mar 2022 • ZhiGang Liu, Xin Luo
Community describes the functional mechanism of a network, making community detection serve as a fundamental graph tool for various real applications like discovery of social circle.
no code implementations • 23 Feb 2023 • ZhiGang Liu, Xin Luo
Community is a fundamental and critical characteristic of an undirected social network, making community detection be a vital yet thorny issue in network representation learning.
1 code implementation • journal 2023 • ZhiGang Liu, Xin Luo, Zidong Wang, Xiaohui Liu
Motivated by this discovery, this paper proposes a novel Constraintinduced Symmetric Nonnegative Matrix Factorization (C-SNMF) model that adopts three-fold ideas: a) Representing a target undirected network with multiple latent feature matrices, thus preserving its representation learning capacity; b) Incorporating a symmetry-regularizer into its objective function, which preserves the symmetry of the learnt low-rank approximation to the adjacency matrix, thereby making the resultant detector precisely illustrate the target network’s symmetry; and c) Introducing a graph-regularizer that preserves local invariance of the network’s intrinsic geometry into its learning objective, thus making the achieved detector well-aware of community structure within the target network.