GraphInception: Convolutional Neural Networks for Collective Classification in Heterogeneous Information Networks

Xiong, Yun; Zhang, Yizhou; Kong, Xiangnan; Chen, Huidi; Zhu, Yangyong

doi:10.1109/tkde.2019.2947458

Cited by 7 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other than working directly with known properties of graphs, implementation of methods of artificial intelligence similar to [27], which would be able to analyze graph coloring and propose fitting permutations for given set of graphs is desirable.…”

Section: Discussionmentioning

confidence: 99%

Optimization of the Functional Decomposition of Parallel and Distributed Computations in Graph Coloring With the Use of High-Performance Computing

Škrinárová

Dudáš

2022

IEEE Access

View full text Add to dashboard Cite

This article presents methods for correct decomposition for high performance computations related to large sets of graphs. These computations contain large number of calls of sequential, recursive algorithm for NP-complete problem -proper edge coloring of graph. Decomposition of this computational problem is not trivial, since the number of recursions in various parts of the computation is different and causes a high load and time imbalance. We designed, implemented and experimentally verified a new decomposition method that significantly reduces the computational time for a large set of graphs (up to 404 million graphs). This method ensures the same duration of computational time for partial subtasks and thus eliminates the need to wait for synchronization of parallel computations.

show abstract

Section: Discussionmentioning

confidence: 99%

Optimization of the Functional Decomposition of Parallel and Distributed Computations in Graph Coloring With the Use of High-Performance Computing

Škrinárová

Dudáš

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…But, if the user has some prior knowledge and it can be ensured that such prior knowledge would not mislead machine learning, then CNN will become even much powerful for data analysis and processing. Successful real-world applications of CNNs include text recognition and classification [45]- [47], face recognition and detection [48], collective classification [49], air quality forecasting [50], etc.…”

Section: Introductionmentioning

confidence: 99%

Knowledge-Based Prediction of Network Controllability Robustness

Lou,

He,

Wang

et al. 2020

Preprint

View full text Add to dashboard Cite

Network controllability robustness reflects how well a networked system can maintain its controllability against destructive attacks. Its measure is quantified by a sequence of values that record the remaining controllability of the network after a sequence of node-removal or edge-removal attacks. Traditionally, the controllability robustness is studied only for directed networks and is determined by attack simulations, which is computationally time consuming or even infeasible. In the present paper, an improved method for predicting the controllability robustness of undirected networks is developed based on machine learning using a group of convolutional neural networks (CNNs). In this scheme, a number of training data generated by simulations are used to train the group of CNNs for classification and prediction, respectively. Extensive experimental studies are carried out, which demonstrate that 1) the proposed method predicts more precisely than the classical single-CNN predictor; 2) the proposed CNN-based predictor provides a better predictive measure than the traditional spectral measures and network heterogeneity.

show abstract

A Tensor-Based Markov Chain Model for Heterogeneous Information Network Collective Classification

Han

Chen

Tan

et al. 2022

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

GraphInception: Convolutional Neural Networks for Collective Classification in Heterogeneous Information Networks

Cited by 7 publications

References 26 publications

Optimization of the Functional Decomposition of Parallel and Distributed Computations in Graph Coloring With the Use of High-Performance Computing

Optimization of the Functional Decomposition of Parallel and Distributed Computations in Graph Coloring With the Use of High-Performance Computing

Knowledge-Based Prediction of Network Controllability Robustness

A Tensor-Based Markov Chain Model for Heterogeneous Information Network Collective Classification

Contact Info

Product

Resources

About