arXiv subjects

Zhiping Lin

Publications and source records attributed to Zhiping Lin.

27 records · Page 2Linked to original sources

arXiv2021

Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view

Graph-based subspace clustering methods have exhibited promising performance. However, they still suffer some of these drawbacks: encounter the expensive time overhead, fail in exploring the explicit clusters, and cannot generalize to unseen data points. In this work, we propose a scalable graph learning framework, seeking to address the above three challenges simultaneously. Specifically, it is based on the ideas of anchor points and bipartite graph. Rather than building a $n\times n$ graph, where $n$ is the number of samples, we construct a bipartite graph to depict the relationship between samples and anchor points. Meanwhile, a connectivity constraint is employed to ensure that the connected components indicate clusters directly. We further establish the connection between our method and the K-means clustering. Moreover, a model to process multi-view data is also proposed, which is linear scaled with respect to $n$. Extensive experiments demonstrate the efficiency and effectiveness of our approach with respect to many state-of-the-art clustering methods.

cs.LG↗

arXiv2020

Accumulated Decoupled Learning: Mitigating Gradient Staleness in Inter-Layer Model Parallelization

Decoupled learning is a branch of model parallelism which parallelizes the training of a network by splitting it depth-wise into multiple modules. Techniques from decoupled learning usually lead to stale gradient effect because of their asynchronous implementation, thereby causing performance degradation. In this paper, we propose an accumulated decoupled learning (ADL) which incorporates the gradient accumulation technique to mitigate the stale gradient effect. We give both theoretical and empirical evidences regarding how the gradient staleness can be reduced. We prove that the proposed method can converge to critical points, i.e., the gradients converge to 0, in spite of its asynchronous nature. Empirical validation is provided by training deep convolutional neural networks to perform classification tasks on CIFAR-10 and ImageNet datasets. The ADL is shown to outperform several state-of-the-arts in the classification tasks, and is the fastest among the compared methods.

cs.LG↗

arXiv2020

GTC: Guided Training of CTC Towards Efficient and Accurate Scene Text Recognition

Connectionist Temporal Classification (CTC) and attention mechanism are two main approaches used in recent scene text recognition works. Compared with attention-based methods, CTC decoder has a much shorter inference time, yet a lower accuracy. To design an efficient and effective model, we propose the guided training of CTC (GTC), where CTC model learns a better alignment and feature representations from a more powerful attentional guidance. With the benefit of guided training, CTC model achieves robust and accurate prediction for both regular and irregular scene text while maintaining a fast inference speed. Moreover, to further leverage the potential of CTC decoder, a graph convolutional network (GCN) is proposed to learn the local correlations of extracted features. Extensive experiments on standard benchmarks demonstrate that our end-to-end model achieves a new state-of-the-art for regular and irregular scene text recognition and needs 6 times shorter inference time than attentionbased methods.

cs.CV↗

arXiv2019

Fully Decoupled Neural Network Learning Using Delayed Gradients

Training neural networks with back-propagation (BP) requires a sequential passing of activations and gradients, which forces the network modules to work in a synchronous fashion. This has been recognized as the lockings (i.e., the forward, backward and update lockings) inherited from the BP. In this paper, we propose a fully decoupled training scheme using delayed gradients (FDG) to break all these lockings. The FDG splits a neural network into multiple modules and trains them independently and asynchronously using different workers (e.g., GPUs). We also introduce a gradient shrinking process to reduce the stale gradient effect caused by the delayed gradients. In addition, we prove that the proposed FDG algorithm guarantees a statistical convergence during training. Experiments are conducted by training deep convolutional neural networks to perform classification tasks on benchmark datasets, showing comparable or better results against the state-of-the-art methods as well as the BP in terms of both generalization and acceleration abilities. In particular, we show that the FDG is also able to train very wide networks (e.g., WRN-28-10) and extremely deep networks (e.g., ResNet-1202). Code is available at https://github.com/ZHUANGHP/FDG.

cs.CV↗

arXiv2018

Gradient-Free Learning Based on the Kernel and the Range Space

In this article, we show that solving the system of linear equations by manipulating the kernel and the range space is equivalent to solving the problem of least squares error approximation. This establishes the ground for a gradient-free learning search when the system can be expressed in the form of a linear matrix equation. When the nonlinear activation function is invertible, the learning problem of a fully-connected multilayer feedforward neural network can be easily adapted for this novel learning framework. By a series of kernel and range space manipulations, it turns out that such a network learning boils down to solving a set of cross-coupling equations. By having the weights randomly initialized, the equations can be decoupled and the network solution shows relatively good learning capability for real world data sets of small to moderate dimensions. Based on the structural information of the matrix equation, the network representation is found to be dependent on the number of data samples and the output dimension.

cs.LG↗

arXiv2018

Deterministic Stretchy Regression

An extension of the regularized least-squares in which the estimation parameters are stretchable is introduced and studied in this paper. The solution of this ridge regression with stretchable parameters is given in primal and dual spaces and in closed-form. Essentially, the proposed solution stretches the covariance computation by a power term, thereby compressing or amplifying the estimation parameters. To maintain the computation of power root terms within the real space, an input transformation is proposed. The results of an empirical evaluation in both synthetic and real-world data illustrate that the proposed method is effective for compressive learning with high-dimensional data.

cs.LG↗

arXiv2016

Constrained Maximum Correntropy Adaptive Filtering

Constrained adaptive filtering algorithms inculding constrained least mean square (CLMS), constrained affine projection (CAP) and constrained recursive least squares (CRLS) have been extensively studied in many applications. Most existing constrained adaptive filtering algorithms are developed under mean square error (MSE) criterion, which is an ideal optimality criterion under Gaussian noises. This assumption however fails to model the behavior of non-Gaussian noises found in practice. Motivated by the robustness and simplicity of maximum correntropy criterion (MCC) in non-Gaussian impulsive noises, this paper proposes a new adaptive filtering algorithm called constrained maximum correntropy criterion (CMCC). Specifically, CMCC incorporates a linear constraint into a MCC filter to solve a constrained optimization problem explicitly. The proposed adaptive filtering algorithm is easy to implement and has low computational complexity, and in terms of convergence accuracy (say lower mean square deviation) and stability, can significantly outperform those MSE based constrained adaptive algorithms in presence of heavy-tailed impulsive noises. Additionally, the mean square convergence behaviors are studied under energy conservation relation, and a sufficient condition to ensure the mean square convergence and the steady-state mean square deviation (MSD) of the proposed algorithm are obtained. Simulation results confirm the theoretical predictions under both Gaussian and non- Gaussian noises, and demonstrate the excellent performance of the novel algorithm by comparing it with other conventional methods.

stat.ML↗

arXiv2016

Topological phase in non-centrosymmetric material NaSnBi

We predict that a non-centrosymmetric material NaSnBi locates in a three-dimensional non-trivial topological phase under ambient pressure based on first-principle calculations. By deriving the effective model around $Γ$ point, we find that the topological phase transition is driven by a Rashba spin-orbital coupling through an odd number of pairs of band touch because of a small anisotropic gap caused by quintic dispersion terms. In contrast to conventional topological insulators, the spin texture of surface Dirac cone is right-handed and the surface states are strikingly different for different surface terminations.

cond-mat.str-el↗

arXiv2014

Tunable Cobalt Vacancies and Related Properties in LaCoxAs2

The origin of transition metal vacancies and their effects on the properties of ThCr2Si2-type compounds have been less studied and poorly understood. Here we carefully investigate the structure, physical properties, and electronic structure for a series of lanthanum cobalt arsenides with nominal composition of LaCoxAs2 (1.6 < = x < = 2.1). It is revealed that the occupancy of Co can be tuned between 1.98(1) and 1.61(1). The structural analyses based on X-ray and neutron diffractions show the existence of Co vacancies results from charge balance due to the formation of bond between As-As. These Co vacancies affect the magnetic and electrical properties greatly, adjusting the Curie temperature from 205 to 47 K and increasing the resistivity by more than 100%. First principles calculations indicate that the Co vacancies weaken the spin polarization and reduce the density of states at the Fermi level, resulting in decreased Curie temperature and increased resistivity, respectively. Our results address the importance of transition metal vacancies in ThCr2Si2-type materials and offer a reliable route to tune the magnetism of ThCr2Si2-type structure.

cond-mat.str-el↗