Encoder Embedding for General Graph and Node Classification
- URL: http://arxiv.org/abs/2405.15473v2
- Date: Tue, 22 Oct 2024 22:48:15 GMT
- Title: Encoder Embedding for General Graph and Node Classification
- Authors: Cencheng Shen,
- Abstract summary: We prove that the encoder embedding matrices satisfies the law of large numbers and the central limit theorem on a per-observation basis.
Under certain condition, it achieves normality on a per-class basis, enabling optimal classification through discriminant analysis.
- Score: 4.178980693837599
- License:
- Abstract: Graph encoder embedding, a recent technique for graph data, offers speed and scalability in producing vertex-level representations from binary graphs. In this paper, we extend the applicability of this method to a general graph model, which includes weighted graphs, distance matrices, and kernel matrices. We prove that the encoder embedding satisfies the law of large numbers and the central limit theorem on a per-observation basis. Under certain condition, it achieves asymptotic normality on a per-class basis, enabling optimal classification through discriminant analysis. These theoretical findings are validated through a series of experiments involving weighted graphs, as well as text and image data transformed into general graph representations using appropriate distance metrics.
Related papers
- What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding [67.59552859593985]
Graph Transformers, which incorporate self-attention and positional encoding, have emerged as a powerful architecture for various graph learning tasks.
This paper introduces first theoretical investigation of a shallow Graph Transformer for semi-supervised classification.
arXiv Detail & Related papers (2024-06-04T05:30:16Z) - Graphon Pooling for Reducing Dimensionality of Signals and Convolutional
Operators on Graphs [131.53471236405628]
We present three methods that exploit the induced graphon representation of graphs and graph signals on partitions of [0, 1]2 in the graphon space.
We prove that those low dimensional representations constitute a convergent sequence of graphs and graph signals.
We observe that graphon pooling performs significantly better than other approaches proposed in the literature when dimensionality reduction ratios between layers are large.
arXiv Detail & Related papers (2022-12-15T22:11:34Z) - Transductive Kernels for Gaussian Processes on Graphs [7.542220697870243]
We present a novel kernel for graphs with node feature data for semi-supervised learning.
The kernel is derived from a regularization framework by treating the graph and feature data as two spaces.
We show how numerous kernel-based models on graphs are instances of our design.
arXiv Detail & Related papers (2022-11-28T14:00:50Z) - Demystifying Graph Convolution with a Simple Concatenation [6.542119695695405]
We quantify the information overlap between graph topology, node features, and labels.
We show that graph concatenation is a simple but more flexible alternative to graph convolution.
arXiv Detail & Related papers (2022-07-18T16:39:33Z) - Graph Encoder Embedding [11.980640637972266]
We propose a lightning fast graph embedding method called graph encoder embedding.
The proposed method has a linear computational complexity and the capacity to process billions of edges within minutes on standard PC.
The speedup is achieved without sacrificing embedding performance.
arXiv Detail & Related papers (2021-09-27T14:49:44Z) - Learning Graphon Autoencoders for Generative Graph Modeling [91.32624399902755]
Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily.
We propose a novel framework called textitgraphon autoencoder to build an interpretable and scalable graph generative model.
A linear graphon factorization model works as a decoder, leveraging the latent representations to reconstruct the induced graphons.
arXiv Detail & Related papers (2021-05-29T08:11:40Z) - Multilayer Clustered Graph Learning [66.94201299553336]
We use contrastive loss as a data fidelity term, in order to properly aggregate the observed layers into a representative graph.
Experiments show that our method leads to a clustered clusters w.r.t.
We learn a clustering algorithm for solving clustering problems.
arXiv Detail & Related papers (2020-10-29T09:58:02Z) - Graph Pooling with Node Proximity for Hierarchical Representation
Learning [80.62181998314547]
We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology.
Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
arXiv Detail & Related papers (2020-06-19T13:09:44Z) - Unsupervised Graph Representation by Periphery and Hierarchical
Information Maximization [18.7475578342125]
Invent of graph neural networks has improved the state-of-the-art for both node and the entire graph representation in a vector space.
For the entire graph representation, most of existing graph neural networks are trained on a graph classification loss in a supervised way.
We propose an unsupervised graph neural network to generate a vector representation of an entire graph in this paper.
arXiv Detail & Related papers (2020-06-08T15:50:40Z) - Block-Approximated Exponential Random Graphs [77.4792558024487]
An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs.
We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions.
Our methods are scalable to sparse graphs consisting of millions of nodes.
arXiv Detail & Related papers (2020-02-14T11:42:16Z) - The Power of Graph Convolutional Networks to Distinguish Random Graph
Models: Short Version [27.544219236164764]
Graph convolutional networks (GCNs) are a widely used method for graph representation learning.
We investigate the power of GCNs to distinguish between different random graph models on the basis of the embeddings of their sample graphs.
arXiv Detail & Related papers (2020-02-13T17:58:42Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.