<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks.</p></abstract>

Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on its application in graph mining is still in an early stage. Here we present Model R, a neural network model created to provide a deep learning approach to the link weight prediction problem. This model uses a node embedding technique that extracts node embeddings (knowledge of nodes) from the known links’ weights (relations between nodes) and uses this knowledge to predict the unknown links’ weights. We demonstrate the power of Model R through experiments and compare it with the stochastic block model and its derivatives. Model R shows that deep learning can be successfully applied to link weight prediction and it outperforms stochastic block model and its derivatives by up to 73% in terms of prediction accuracy. We analyze the node embeddings to confirm that closeness in embedding space correlates with stronger relationships as measured by the link weight. We anticipate this new approach will provide effective solutions to more graph mining tasks.

On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction

School of Electrical Engineering and Computer Science

Journal of Artificial Intelligence and Soft Computing Research

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Deep learning has been successful in various domains including image recognition, speech recognition and natural language processing. However, the research on...

On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction

Data publikacji: 20 sie 2018

Zakres stron: 21 - 40

Otrzymano: 20 paź 2017

Przyjęty: 13 lis 2017

DOI: https://doi.org/10.2478/jaiscr-2018-0022

Słowa kluczowe
Deep learning, Neural networks, Machine learning, Graph mining, Link weight prediction, Predictive models, Node embeddings

© 2019 Yuchen Hou et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

On Graph Mining With Deep Learning: Introducing Model R for Link Weight Prediction

Data publikacji: 20 sie 2018

Zakres stron: 21 - 40

Otrzymano: 20 paź 2017

Przyjęty: 13 lis 2017

DOI: https://doi.org/10.2478/jaiscr-2018-0022

Słowa kluczoweDeep learning, Neural networks, Machine learning, Graph mining, Link weight prediction, Predictive models, Node embeddings

© 2019 Yuchen Hou et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Słowa kluczowe
Deep learning, Neural networks, Machine learning, Graph mining, Link weight prediction, Predictive models, Node embeddings