# Learning Topological Representation for Networks via Hierarchical Sampling

@article{Fu2019LearningTR, title={Learning Topological Representation for Networks via Hierarchical Sampling}, author={Guoji Fu and Chengbin Hou and Xin Yao}, journal={2019 International Joint Conference on Neural Networks (IJCNN)}, year={2019}, pages={1-8} }

The topological information is essential for studying the relationship between nodes in a network. Recently, Network Representation Learning (NRL), which projects a network into a low-dimensional vector space, has been shown their advantages in analyzing large-scale networks. However, most existing NRL methods are designed to preserve the local topology of a network and they fail to capture the global topology. To tackle this issue, we propose a new NRL framework, named HSRL, to help existingâ€¦Â Expand

#### Figures, Tables, and Topics from this paper

#### 8 Citations

GloDyNE: Global Topology Preserving Dynamic Network Embedding

- Computer Science
- ArXiv
- 2020

A novel node selecting strategy to diversely select the representative nodes over a network, coordinated with a new incremental learning paradigm of Skip-Gram based embedding approach is proposed, which significantly outperforms other methods in the graph reconstruction task, which demonstrates its ability of global topology preservation. Expand

Marc: Multi-Granular Representation Learning for Networks Based on the 3-Clique

- Computer Science
- IEEE Access
- 2019

A novel algorithm multi-granular representation learning for networks based on the 3-clique named Marc makes the representations of the current network be formed by both considering the structure of this granular network and inheriting the coarser network representation results. Expand

A multi-granular network representation learning method

- Computer Science
- Granular Computing
- 2019

A Multi-Granular Network Representation Learning method based on Quotient Space Theory (MG_NRL), which can preserve global and local structure at different granularities and significantly outperforms other state-of-the-art methods on multi-label classification task. Expand

Graph Representation Learning by Ensemble Aggregating Subgraphs via Mutual Information Maximization

- Computer Science
- ArXiv
- 2021

A self-supervised learning method to enhance the representations of graphlevel learned by Graph Neural Networks and an ensemble-learning like subgraph method is proposed to get a comprehensive understanding of the graph structure. Expand

Graph Cross Networks with Vertex Infomax Pooling

- Computer Science, Mathematics
- NeurIPS
- 2020

A novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph, which includes a novel vertex infomax pooling (VIPool), and a novel feature-crossing layer, enabling feature interchange across scales. Expand

Detecting protein complex based on hierarchical compressing network embedding

- Computer Science
- 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
- 2019

A novel protein complex detection method based on hierarchical compressing network embedding, named DPC-HCNE, which can preserve both the localTopological information and global topological information of a PPI network. Expand

Graph Cross Networks with Vertex Infomax Pooling /Author=Li, Maosen; Chen, Siheng; Zhang, Ya /CreationDate=December 16, 2020 /Subject=Artificial Intelligence, Machine Learning, Signal Processing

- 2020

We propose a novel graph cross network (GXN) to achieve comprehensive feature learning from multiple scales of a graph. Based on trainable hierarchical representations of a graph, GXN enables theâ€¦ Expand

GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding

- Computer Science, Mathematics
- ICLR
- 2020

Experiments show that GraphZoom can substantially increase the classification accuracy and significantly accelerate the entire graph embedding process by up to 40.8x, when compared to the state-of-the-art unsupervised embedding methods. Expand

#### References

SHOWING 1-10 OF 28 REFERENCES

node2vec: Scalable Feature Learning for Networks

- Computer Science, Mathematics
- KDD
- 2016

In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods. Expand

Structural Deep Network Embedding

- Computer Science
- KDD
- 2016

This paper proposes a Structural Deep Network Embedding method, namely SDNE, which first proposes a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non- linear network structure and exploits the first-order and second-order proximity jointly to preserve the network structure. Expand

Deep Neural Networks for Learning Graph Representations

- Computer Science
- AAAI
- 2016

A novel model for learning graph representations, which generates a low-dimensional vector representation for each vertex by capturing the graph structural information directly, and which outperforms other stat-of-the-art models in such tasks. Expand

LINE: Large-scale Information Network Embedding

- Computer Science
- WWW
- 2015

A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures. Expand

HARP: Hierarchical Representation Learning for Networks

- Computer Science
- AAAI
- 2018

HARP is a general meta-strategy to improve all of the state-of-the-art neural algorithms for embedding graphs, including DeepWalk, LINE, and Node2vec, and it is demonstrated that applying HARP's hierarchical paradigm yields improved implementations for all three of these methods. Expand

Graph Embedding Techniques, Applications, and Performance: A Survey

- Computer Science
- Knowl. Based Syst.
- 2018

A comprehensive and structured analysis of various graph embedding techniques proposed in the literature, and the open-source Python library, named GEM (Graph Embedding Methods, available at https://github.com/palash1992/GEM ), which provides all presented algorithms within a unified interface to foster and facilitate research on the topic. Expand

GraRep: Learning Graph Representations with Global Structural Information

- Computer Science
- CIKM
- 2015

A novel model for learning vertex representations of weighted graphs that integrates global structural information of the graph into the learning process and significantly outperforms other state-of-the-art methods in such tasks. Expand

DeepWalk: online learning of social representations

- Computer Science
- KDD
- 2014

DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection. Expand

Semi-Supervised Classification with Graph Convolutional Networks

- Computer Science, Mathematics
- ICLR
- 2017

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. Expand

Distributed large-scale natural graph factorization

- Computer Science
- WWW '13
- 2013

This work proposes a novel factorization technique that relies on partitioning a graph so as to minimize the number of neighboring vertices rather than edges across partitions, and decomposition is based on a streaming algorithm. Expand