Gated Graph Convolutional Recurrent Neural Networks

Ruiz, Luana; Gama, Fernando; Ribeiro, Alejandro

doi:10.23919/eusipco.2019.8902995

Cited by 30 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…definition 2]. We denote W n , the induced graphon by template graph S n as in (8). By introducing T ≥c [H nL ] gf , the graph filter with filter function h ≥c Lgf on graphon W n , we can use the triangle inequality to obtain,…”

Section: Be the Graphon Convoutional Filters With Filter Function H mentioning

confidence: 99%

“…Graph Neural Networks (GNNs) are deep convolutional architectures formed by a succession of layers where each layer composes a graph convolution and a pointwise nonlinearity [1,2]. Tailored to network data, GNNs have been used in a variety of applications including recommendation systems [3][4][5][6], and Markov chains [7][8][9], and fields such as biology [10][11][12][13] and robotics [14][15][16]. Their success in these fields and applications provides ample empirical evidence of the ability of GNNs to generalize to unseen data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Increase and Conquer: Training Graph Neural Networks on Growing Graphs

Juan¹,

Ruiz²,

Ribeiro³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Graph neural networks (GNNs) use graph convolutions to exploit network invariances and learn meaningful features from network data. However, on large-scale graphs convolutions incur in high computational cost, leading to scalability limitations. Leveraging the graphon -the limit object of a graph -in this paper we consider the problem of learning a graphon neural network (WNN) -the limit object of a GNN -by training GNNs on graphs sampled Bernoulli from the graphon. Under smoothness conditions, we show that: (i) the expected distance between the learning steps on the GNN and on the WNN decreases asymptotically with the size of the graph, and (ii) when training on a sequence of growing graphs, gradient descent follows the learning direction of the WNN. Inspired by these results, we propose a novel algorithm to learn GNNs on large-scale graphs that, starting from a moderate number of nodes, successively increases the size of the graph during training. This algorithm is benchmarked on both a recommendation system and a decentralized control problem where it is shown to retain comparable performance, to its large-scale counterpart, at a reduced computational cost.Preprint. Under review.

show abstract

Section: Be the Graphon Convoutional Filters With Filter Function H mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Increase and Conquer: Training Graph Neural Networks on Growing Graphs

Juan¹,

Ruiz²,

Ribeiro³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The work [25] is based on the assumption that well-predicting edge and neighborhood features already exist, which is not the case in our situation. Authors of [24] propose another neural network for working with dynamic graphs but focus on the change of the graph structure over time. Some of these approaches can be modified to be applied in our scenario, but these modifications are non-trivial and require separate research.…”

Section: Related Workmentioning

confidence: 99%

Linking bank clients using graph neural networks powered by rich transactional data

Shumovskaia

Fedyanin

Sukharev

et al. 2021

Int J Data Sci Anal

View full text Add to dashboard Cite

Financial institutions obtain enormous amounts of data about client transactions and money transfers, which can be considered as a large graph dynamically changing in time. In this work, we focus on the task of predicting new interactions in the network of bank clients and treat it as a link prediction problem. We propose a new graph neural network model, which uses not only the topological structure of the network but rich time-series data available for the graph nodes and edges. We evaluate the developed method using the data provided by a large European bank for several years. The proposed model outperforms the existing approaches, including other neural network models, with a significant gap in ROC AUC score on link prediction problem and also allows to improve the quality of credit scoring.

show abstract

“…Following the success of GGNN models (Beck et al, 2018;Ruiz et al, 2019), we use GGNNs to capture both the mathematical relations among variables and quantities and the real-life associations among entities in the MWPs. Specifically, let G = {V, E} be an edge-enhanced Levi graph where V and E are the sets of nodes and edges.…”

Section: Gated Graph Neural Encodingmentioning

confidence: 99%

Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations

Liu¹,

Qian²,

Ding³

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

There is an increasing interest in the use of mathematical word problem (MWP) generation in educational assessment. Different from standard natural question generation, MWP generation needs to maintain the underlying mathematical operations between quantities and variables, while at the same time ensuring the relevance between the output and the given topic. To address above problem, we develop an end-to-end neural model to generate diverse MWPs in real-world scenarios from commonsense knowledge graph and equations. The proposed model (1) learns both representations from edge-enhanced Levi graphs of symbolic equations and commonsense knowledge; (2) automatically fuses equation and commonsense knowledge information via a self-planning module when generating the MWPs. Experiments on an educational gold-standard set and a large-scale generated MWP set show that our approach is superior on the MWP generation task, and it outperforms the SOTA models in terms of both automatic evaluation metrics, i.e., BLEU-4, ROUGE-L, Self-BLEU, and human evaluation metrics, i.e., equation relevance, topic relevance, and language coherence. To encourage reproducible results, we make our code and MWP dataset public available at https:// github.com/tal-ai/MaKE_EMNLP2021.

show abstract

Gated Graph Convolutional Recurrent Neural Networks

Cited by 30 publications

References 15 publications

Increase and Conquer: Training Graph Neural Networks on Growing Graphs

Increase and Conquer: Training Graph Neural Networks on Growing Graphs

Linking bank clients using graph neural networks powered by rich transactional data

Mathematical Word Problem Generation from Commonsense Knowledge Graph and Equations

Contact Info

Product

Resources

About