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

Hou, Yuchen; Holder, Lawrence B.

doi:10.2478/jaiscr-2018-0022

Cited by 10 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hou et. al [12] developed Model R a deep neural network model that aims to predict the existence and the weight of new edges (links) within a graph. Our model comes as support for the prediction of weights of both existing and new edges for which features are known, given a timestamp.…”

Section: Link Weight Predictionmentioning

confidence: 99%

On the Quality of Compositional Prediction for Prospective Analytics on Graphs

Lyan¹,

Amblard²,

Jézéquel³

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Recently, micro-learning has been successfully applied to various scenarios, such as graph optimization (e.g. power grid management). In these approaches, ad-hoc models of local data are built instead of one large model on the overall data set. Micro-learning is typically useful for incremental, what-if/prospective scenarios, where one has to perform step-by-step decisions based on local properties. A common feature of these applications is that the predicted properties (such as speed of a bus line) are compositions of smaller parts (e.g. the speed on each bus inter-stations along the line). But little is known about the quality of such predictions when generalized at a larger scale.In this paper we propose a generic technique that embeds machine-learning for graph-based compositional prediction, that allows 1) the prediction of the behaviour of composite objects, based on the predictions of their sub-parts and appropriate composition rules, and 2) the production of rich prospective analytics scenarios, where new objects never observed before can be predicted based on their simpler parts. We show that the quality of such predictions compete with macro-learning ones, while enabling prospective scenarios. We assess our work on a real size, operational bus network data set.

show abstract

Section: Link Weight Predictionmentioning

confidence: 99%

On the Quality of Compositional Prediction for Prospective Analytics on Graphs

Lyan¹,

Amblard²,

Jézéquel³

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…Deep learning has become very popular both as a field of study for researchers [8,24,33] and as a practical tool in many applications [12,36]. Different deep structures allow handling many real-world tasks, with effectiveness unimaginable just a few years ago.…”

Section: Introductionmentioning

confidence: 99%

On Training Deep Neural Networks Using a Streaming Approach

Duda

Jaworski

Cader

et al. 2019

Journal of Artificial Intelligence and Soft Computing Research

View full text Add to dashboard Cite

In recent years, many deep learning methods, allowed for a significant improvement of systems based on artificial intelligence methods. Their effectiveness results from an ability to analyze large labeled datasets. The price for such high accuracy is the long training time, necessary to process such large amounts of data. On the other hand, along with the increase in the number of collected data, the field of data stream analysis was developed. It enables to process data immediately, with no need to store them. In this work, we decided to take advantage of the benefits of data streaming in order to accelerate the training of deep neural networks. The work includes an analysis of two approaches to network learning, presented on the background of traditional stochastic and batch-based methods.

show abstract