Journal Article10.1145/3441456
Elastic Embedding through Graph Convolution-based Regression for Semi-supervised Classification
5
TL;DR: The proposed Graph Convolution-based Semi-supervised Embedding paves the way to new theoretical and application perspectives related to the non-linear embedding, which can tackle the problem of over-fitting on neighborhood structures for image data.
read more
Abstract: This article introduces a scheme for semi-supervised learning by estimating a flexible non-linear data representation that exploits Spectral Graph Convolutions structure Structured data are exploited in order to determine non-linear and linear models The introduced scheme takes advantage of data-driven graphs at two levels First, it incorporates manifold smoothness that is naturally encoded by the graph itself Second, the regression model is built on the convolved data samples that are derived from the data and their associated graph The proposed semi-supervised embedding can tackle the problem of over-fitting on neighborhood structures for image data The proposed Graph Convolution-based Semi-supervised Embedding paves the way to new theoretical and application perspectives related to the non-linear embedding Indeed, building flexible models that adopt convolved data samples can enhance both the data representation and the final performance of the learning system Several experiments are conducted on six image datasets for comparing the introduced scheme with some state-of-the-art semi-supervised approaches This empirical evaluation shows the effectiveness of the proposed embedding scheme
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Multi-graph Fusion Graph Convolutional Networks with pseudo-label supervision
TL;DR: In this article , the authors proposed Multi-graph Fusion Graph Convolutional Networks with pseudo-label supervision (MFGCN), which learns a connected embedding by fusing the multi-graphs and node features.
19
Learning the Explainable Semantic Relations via Unified Graph Topic-Disentangled Neural Networks
TL;DR: TDG as discussed by the authors proposes a graph topic module to handle node features to construct independent and explainable semantic subspaces, then the reasonable relation topics are assigned to each graph relation via a neighborhood routing mechanism.
17
DropAGG: Robust Graph Neural Networks via Drop Aggregation
TL;DR: Wang et al. as mentioned in this paper proposed Drop Aggregation (DropAGG) which randomly selects a certain rate of nodes to participate in information aggregation to mitigate the over-smoothing issue.
12
I2DKPCN: an unsupervised deep learning network
Ruyi Zhao,Fanhuai Shi +1 more
TL;DR: The filters of the convolutional layer are learned by I2DKPCA, which combined the 2DPCA with kernel method and incremental learning, the non-linear problem was solved and the computational time was reduced.
2
References
•Posted Content
Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf,Max Welling +1 more
TL;DR: A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
22.7K
Nonlinear dimensionality reduction by locally linear embedding.
Sam T. Roweis,Lawrence K. Saul +1 more
TL;DR: Locally linear embedding (LLE) is introduced, an unsupervised learning algorithm that computes low-dimensional, neighborhood-preserving embeddings of high-dimensional inputs that learns the global structure of nonlinear manifolds.
A global geometric framework for nonlinear dimensionality reduction.
TL;DR: An approach to solving dimensionality reduction problems that uses easily measured local metric information to learn the underlying global geometry of a data set and efficiently computes a globally optimal solution, and is guaranteed to converge asymptotically to the true structure.
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Svetlana Lazebnik,Cordelia Schmid,Jean Ponce +2 more
- 17 Jun 2006
TL;DR: This paper presents a method for recognizing scene categories based on approximate global geometric correspondence that exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories.
A comparative study of texture measures with classification based on featured distributions
TL;DR: This paper evaluates the performance both of some texture measures which have been successfully used in various applications and of some new promising approaches proposed recently.
7.3K