Graph Based Semi-Supervised Learning via Structure Preserving Low-Rank Representation

Peng, Yong; Long, Xianzhong; Lu, Bao-Liang

doi:10.1007/s11063-014-9396-z

Cited by 10 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The manifold low-rank representation (MLRR) [18] first uses a sparse learning objective to identify the data manifold and then incorporates the manifold information into low-rank representation as a regularizer. Additionally, [19] proposed preserving the structure information of data from two aspects: local affinity and distant repulsion. Li and Fu proposed constructing graph based on low-rank coding and -matching constraint for obtaining a sparse and balanced graph [20].…”

Section: Introductionmentioning

confidence: 99%

Manifold Adaptive Kernelized Low‐Rank Representation for Semisupervised Image Classification

et al. 2018

Self Cite

View full text Add to dashboard Cite

Constructing a powerful graph that can effectively depict the intrinsic connection of data points is the critical step to make the graph-based semisupervised learning algorithms achieve promising performance. Among popular graph construction algorithms, low-rank representation (LRR) is a very competitive one that can simultaneously explore the global structure of data and recover the data from noisy environments. Therefore, the learned low-rank coefficient matrix in LRR can be used to construct the data affinity matrix. Consider the existing problems such as the following: (1) the essentially linear property of LRR makes it not appropriate to process the possible nonlinear structure of data and (2) learning performance can be greatly enhanced by exploring the structure information of data; we propose a new manifold kernelized low-rank representation (MKLRR) model that can perform LRR in the data manifold adaptive kernel space. Specifically, the manifold structure can be incorporated into the kernel space by using graph Laplacian and thus the underlying geometry of data is reflected by the wrapped kernel space. Experimental results of semisupervised image classification tasks show the effectiveness of MKLRR. For example, MKLRR can, respectively, obtain 96.13%, 98.09%, and 96.08% accuracies on ORL, Extended Yale B, and PIE data sets when given 5, 20, and 20 labeled face images per subject.

show abstract

Section: Introductionmentioning

confidence: 99%

Manifold Adaptive Kernelized Low‐Rank Representation for Semisupervised Image Classification

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The scheme we focus on is to exploit the Graph Neural Networks (GNNs) to extract the latent interaction graph from the dynamic flying trajectory data. GNNs [22][23][24] are a class of Neural Network model that can process the dynamic graph structure data. The architecture of GNNs [25] is constructed from the graph G = (V , E) with a set of nodes V and edges E. The approaches to deal with the task of the latent interaction graph extraction are closely associated with the methods of graph generation [26].…”

Section: Graph Neural Network (Gnns)mentioning

confidence: 99%

“…In the DCII, we invoke the traditional graph model [35] and use the node degree to rank the influential nodes. The node with maximum node degree can be recognized as the core node.…”

Section: Identifying the Influential Nodes Of Drone Swarmmentioning

confidence: 99%

Identification of Influential Nodes for Drone Swarm Based on Graph Neural Networks

Wang

Zhuang

Xie

2021

Neural Process Lett

View full text Add to dashboard Cite

Accurately tracking the influential nodes in swarm is the key to improve the control or defense against the drone combat. But the identification of influential nodes is intractable due to hardly capturing the pattern information of the running drones based on the traditional Graph Theory. To tackle this issue, in this paper, we propose a novel framework to identify the influential nodes, which includes Latent Interaction Graph Extraction (LIGE), Degree Centrality based Influential Inference (DCII) and Formation Stability Coefficient based Re-ranking (FSCR). LIGE is employed to reconstruct the latent interaction graph from the dynamic trajectory data by exploiting the encoder in Neural Relational Inference. DCII invokes the traditional graph model and measures the significance of nodes. In the re-ranking module FSCR, we introduce a novel metric, the formation stability coefficient, to measure swarm formation stability and re-ranking the candidates. The experimental results on the Drone swarm datasets demonstrate that our framework can effectively identify the influential nodes of drone swarm. The extracting time in LIGE is relatively long, which makes it difficult to recognize the core node within the limit time. By optimizing the encoder structure, the extraction time can be reduced to at least twice the original.

show abstract

“…There are several versions of supervised dictionary learning for machine learning application [11,12]. However in this work we are only interested in the unsupervised version.…”

Section: Background Representation Learningmentioning

confidence: 99%

Majorization Minimization Technique for Optimally Solving Deep Dictionary Learning

Singhal

Majumdar

2017

Neural Process Lett

View full text Add to dashboard Cite

The total number of words of the manuscript, including entire text from title page to figure legends: 5050The number of words of the abstract: 199The number of figures: 7The number of tables: 2 Deep Dictionary Learning Page nr. 2 of 20 2The concept of deep dictionary learning has been recently proposed. Unlike shallow dictionary learning which learns single level of dictionary to represent the data, it uses multiple layers of dictionaries. So far, the problem could only be solved in a greedy fashion; this was achieved by learning a single layer of dictionary in each stage where the coefficients from the previous layer acted as inputs to the subsequent layer (only the first layer used the training samples as inputs). This was not optimal; there was feedback from shallower to deeper layers but not the other way.This work proposes an optimal solution to deep dictionary learning whereby all the layers of dictionaries are solved simultaneously. We employ the Majorization Minimization approach.Experiments have been carried out on benchmark datasets; it shows that optimal learning indeed improves over greedy piecemeal learning. Comparison with other unsupervised deep learning tools (stacked denoising autoencoder, deep belief network, contractive autoencoder and K-sparse autoencoder) show that our method supersedes their performance both in accuracy and speed.

show abstract

Graph Based Semi-Supervised Learning via Structure Preserving Low-Rank Representation

Cited by 10 publications

References 21 publications

Manifold Adaptive Kernelized Low‐Rank Representation for Semisupervised Image Classification

Manifold Adaptive Kernelized Low‐Rank Representation for Semisupervised Image Classification

Identification of Influential Nodes for Drone Swarm Based on Graph Neural Networks

Majorization Minimization Technique for Optimally Solving Deep Dictionary Learning

Contact Info

Product

Resources

About