Dynamic graph convolutional networks

Manessi, Franco; Rozza, Alessandro; Manzo, Mario

doi:10.1016/j.patcog.2019.107000

Cited by 288 publications

(128 citation statements)

References 21 publications

Supporting

Mentioning

114

Contrasting

Order By: Relevance

“…Deep learning has been applied successfully in the past to graph classification problems [9] and to dynamic graph prediction problems [10]. Many different forms of neural networks exist, and these different forms are frequently used in combination.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

“…Neural networks are well-suited to our problem because a single network can predict the simultaneous evolution of multiple features. Our network architecture exploits the capabilities of a graph convolutional network (gCNs) [9] to recognize features from the reduced graph representation of large fracture networks, coupled with a recurrent neural network (RNN) [10] to model the evolution of those features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks

Schwarzer

Rogan

Ruan

et al. 2019

Computational Materials Science

View full text Add to dashboard Cite

We propose a machine learning approach to address a key challenge in materials science: predicting how fractures propagate in brittle materials under stress, and how these materials ultimately fail. Our methods use deep learning and train on simulation data from high-fidelity models, emulating the results of these models while avoiding the overwhelming computational demands associated with running a statistically significant sample of simulations. We employ a graph convolutional network that recognizes features of the fracturing material and a recurrent neural network that models the evolution of these features, along with a novel form of data augmentation that compensates for the modest size of our training data. We simultaneously generate predictions for qualitatively distinct material properties. Results on fracture damage and length are within 3% of their simulated values, and results on time to material failure, which is notoriously difficult to predict even with highfidelity models, are within approximately 15% of simulated values. Once trained, our neural networks generate predictions within seconds, rather than the hours needed

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks

Schwarzer

Rogan

Ruan

et al. 2019

Computational Materials Science

View full text Add to dashboard Cite

show abstract

“…Many works that handle dynamic graphs have used them as baseline methods. For instance, node2vec in [17,20,29,30], LINE (NetMF) in [18,20], DeepWalk in [17,18,20]. Since in our problem, the vertices arrive in a streaming fashion, each of the baselines is utilized through being retrained on the entire new graph.…”

Section: Compared Baseline Methodsmentioning

confidence: 99%

Real-Time Streaming Graph Embedding Through Local Actions

Liu¹,

Hsieh²,

Duffield³

et al. 2019

Companion Proceedings of the 2019 World Wide Web Conference

View full text Add to dashboard Cite

Recently, considerable research attention has been paid to network embedding, a popular approach to construct feature vectors of vertices in latent space. Due to the curse of dimensionality and sparsity in graphical datasets, this approach has become indispensable for machine learning tasks over large networks. The majority of existing literature has considered this technique under the assumption that the network is static. However, networks in many applications, including social networks, collaboration networks, and recommender systems, nodes and edges accrue to a growing network as a streaming. Moreover, high-throughput production machine learning systems require to promptly generate representations for new vertices. A small number of very recent results have address the problem of embedding for dynamic networks. However, they either rely on knowledge of vertex attributes, suffer high-time complexity, or need to be re-trained without closed-form expression. Thus the approach of adapting of the existing methods designed for static networks or dynamic networks to the streaming environment faces non-trivial technical challenges.These challenges motivate developing new approaches to the problems of streaming network embedding. In this paper We propose a new framework that is able to generate latent features for new vertices with high efficiency and low complexity under specified iteration rounds. We formulate a constrained optimization problem for the modification of the representation resulting from a stream arrival. We show this problem has no closed-form solution and instead develop an online approximation solution. Our solution follows three steps: (1) identify vertices affected by newly arrived ones, (2) generating latent features for new vertices, and (3) updating the latent features of the most affected vertices. The generated representations are provably feasible and not far from the optimal ones in terms of expectation. Multi-class classification and clustering on five real-world networks demonstrate that our model can efficiently update vertex representations and simultaneously achieve comparable or even better performance compared with model retraining.

show abstract

“…The E-LSTM-D approach [38] is also extremely similar to this model. • D-GCN: [20], [21]: A dynamic GCN, similar to approaches proposed in [20] and [21]. Here three stacked GCN layers are used to capture structural information with an LSTM unit used to learn temporal information and produce the final embeddings.…”

Section: • Gae [13]: a Non-probabilistic Graph Convolutionalmentioning

confidence: 99%

Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions

Bonner

Atapour-Abarghouei

Jackson

et al. 2019

2019 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Graphs have become a crucial way to represent large, complex and often temporal datasets across a wide range of scientific disciplines. However, when graphs are used as input to machine learning models, this rich temporal information is frequently disregarded during the learning process, resulting in suboptimal performance on certain temporal infernce tasks. To combat this, we introduce Temporal Neighbourhood Aggregation (TNA), a novel vertex representation model architecture designed to capture both topological and temporal information to directly predict future graph states. Our model exploits hierarchical recurrence at different depths within the graph to enable exploration of changes in temporal neighbourhoods, whilst requiring no additional features or labels to be present. The final vertex representations are created using variational sampling and are optimised to directly predict the next graph in the sequence. Our claims are reinforced by extensive experimental evaluation on both real and synthetic benchmark datasets, where our approach demonstrates superior performance compared to competing methods, out-performing them at predicting new temporal edges by as much as 23% on real-world datasets, whilst also requiring fewer overall model parameters.

show abstract

Dynamic graph convolutional networks

Cited by 288 publications

References 21 publications

Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks

Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks

Real-Time Streaming Graph Embedding Through Local Actions

Temporal Neighbourhood Aggregation: Predicting Future Links in Temporal Graphs via Recurrent Variational Graph Convolutions

Contact Info

Product

Resources

About