• Corpus ID: 199064313

Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview

@article{Zhang2019GraphNN,
  title={Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview},
  author={Jiawei Zhang},
  journal={ArXiv},
  year={2019},
  volume={abs/1908.00187}
}
Graph neural networks denote a group of neural network models introduced for the representation learning tasks on graph data specifically. Graph neural networks have been demonstrated to be effective for capturing network structure information, and the learned representations can achieve the state-of-the-art performance on node and graph classification tasks. Besides the different application scenarios, the architectures of graph neural network models also depend on the studied graph types a… 

HDGI: An Unsupervised Graph Neural Network for Representation Learning in Heterogeneous Graph

TLDR
An unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation learning is proposed, which effectively learns high-level node representations that can be utilized in downstream graph-related tasks by maximizing local-global mutual information.

Heterogeneous Deep Graph Infomax

TLDR
An unsupervised graph neural network Heterogeneous Deep Graph Infomax (HDGI) for heterogeneous graph representation learning is proposed, which uses the meta-path structure to analyze the connections involving semantics in heterogeneous graphs and utilize graph convolution module and semantic-level attention mechanism to capture local representations.

Get Rid of Suspended Animation: Deep Diffusive Neural Network for Graph Representation Learning

TLDR
A new graph neural network, namely DIFNET (Graph Diffusive Neural Network), for deep graph representation learning and node classification, which utilizes both neural gates and graph residual learning for node hidden state modeling and includes an attention mechanism for node neighborhood information diffusion.

Graph Neural Distance Metric Learning with Graph-Bert

TLDR
GB-DISTANCE (GRAPH-BERT based Neural Distance) can out-perform the existing baseline methods, especially the recent graph neural network model based graph metrics, with a significant gap in computing the graph distance.

Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification

TLDR
A new graph neural network, namely DIFNET (Graph Diffusive Neural Network), for graph representation learning and node classification, which utilizes both neural gates and graph residual learning for node hidden state modeling, and includes an attention mechanism for node neighborhood information diffusion.

How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey

TLDR
This survey carefully examines various graph-based deep learning architectures in many traffic applications to discuss their shared deep learning techniques, clarifying the utilization of each technique in traffic tasks.

Segmented Graph-Bert for Graph Instance Modeling

TLDR
This paper re-designs GRAPH-BERT with a segmented architecture and introduces three different strategies to unify the graph instance sizes, i.e., full-input, padding/pruning and segment shifting, respectively, which can out-perform the comparison methods on six out of them with significant performance advantages.

Graph Representation Learning via Contrasting Cluster Assignments

TLDR
A novel unsupervised graph representation model by contrasting cluster assignments, called as GRCCA, that can keep a balanced aggregation of local and global information, and gets insight into the elusive association between nodes beyond graph topology.

Traffic Forecasting Based on Integration of Adaptive Subgraph Reformulation and Spatio-Temporal Deep Learning Model

TLDR
A novel traffic forecasting framework is proposed by integrating the dynamic association of traffic nodes with the spatio-temporal deep learning model, which consistently outperforms other GNN (Graph Neural Network)-based state-of-the-art baselines for various forecasting intervals on a real-world dataset.

DEAM: Adaptive Momentum with Discriminative Weight for Stochastic Optimization

TLDR
A novel optimization algorithm, namely Discriminative wEight on Adaptive Momentum (DEAM), which proposes to compute the momentum weight automatically based on the discriminative angle and contains a novel backtrack term, which restricts redundant updates when the correction of the last step is needed.

References

SHOWING 1-7 OF 7 REFERENCES

IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification

TLDR
A novel model named Isomorphic Neural Network (IsoNN), which learns the graph representation by extracting its isomorphic features via the graph matching between input graph and templates, and can demonstrate the effectiveness of ISONN, especially compared with both classic and state-of-the-art graph classification methods.

Semi-Supervised Classification with Graph Convolutional Networks

TLDR
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.

Inductive Representation Learning on Large Graphs

TLDR
GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.

Graph Neural Lasso for Dynamic Network Regression

TLDR
A novel graph neural network, namely graph neural lasso (GNL), will be proposed in this paper, to model the real-time changes of nodes in the network and extends gated diffusive unit (GDU) to the regression scenario and uses it as the basic neuron unit.

Structural Deep Brain Network Mining

TLDR
A Structural Deep Brain Network mining method to learn highly non-linear and structure-preserving representations of brain networks and a deep feature learning framework for combining supervised learning and unsupervised learning in a small-scale setting by augmenting Convolutional Neural Network with decoding pathways for reconstruction.

SEGEN: Sample-Ensemble Genetic Evolutional Network Model

TLDR
A new representation learning model, namely "Sample-Ensemble Genetic Evolutional Network" (SEGEN), which can serve as an alternative approach to deep learning models, and which requires far less data, fewer computational resources and parameter tuning works, but has sound theoretic interpretability of the learning process and results.

Fake News Detection with Deep Diffusive Network Model

TLDR
This paper introduces a novel automatic fake news credibility inference model, namely FakeDetector, which builds a deep diffusive network model to learn the representations of news articles, creators and subjects simultaneously.