Dynamic Graph Convolutional Networks

By Franco Manessi, Alessandro Rozza, Mario Manzo. 2017

468 citations recorded by the source corpus.

Abstract In many different classification tasks it is required to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change over time. The goal is to exploit existing neural network architectures to model datasets that are best represented with graph structures that change over time. To the best of the authors’ knowledge, this task has not been addressed using these kinds of architectures. Two novel approaches are proposed, which combine Long Short-Term Memory networks and Graph Convolutional Networks to learn long short-term dependencies together with graph structure. The advantage provided by the proposed methods is confirmed by the results achieved on four real world datasets: an increase of up to 12 percentage points in Accuracy and F1 scores for vertex-based semi-supervised classification and up to 2 percentage points in Accuracy and F1 scores for graph-based supervised classification.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning to Simulate Complex Physics with Graph Networks (2020, background): “…et al., 2019; Sanchez-Gonzalez et al., 2019), as well as non-physical systems, such as multi-agent dynamics (Tacchetti et al., 2018; Sun et al., 2019), algorithm execution (Velikovi et al., 2020), and other dynamic graph settings (Trivedi et al., 2019; 2017; Yan et al., 2018; Manessi et al., 2020).”
Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks (2021, background): “Most of the above models are not inductive because they associate each node with an onehot identity (or the corresponding row of the adjacency matrix, or a free-trained vector) (Li et al., 2018; Chen et al., 2019; Kumar et al., 2019; Hajiramezanali et al., 2019; Sankar et al., 2020; Manessi et al., ”
Graph Learning: A Survey (2021, unknown): “Zhang et al. [18] summarized deep learning based methods for graphs, such as graph neural networks (GNNs), graph convolutional networks (GCNs) and graph auto-encoders (GAEs).”
Incremental Training of Graph Neural Networks on Temporal Graphs under Distribution Shift (2020, background): “Regarding dynamic graphs , several works consider a ﬁxed vertex set and stack recurrent modules on top of graph convolutional modules [23,15].”
AutoGraph: Automated Graph Neural Network (2020, methodology): “Some GNN models have been proposed and obtain promising results on some graph tasks, such as node classiﬁcation [8,7,20,14], link prediction [23] and clustering [22].”
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors (2018, background): “This paves the way to the appliance of graph convolutional networks [25].”
Temporal Graph Networks for Deep Learning on Dynamic Graphs (2020, methodology): “In the latter case, the embeddings are either aggregated by taking a weighted sum [67, 74], ﬁt to time series models [30, 24, 11, 44], used as components in RNNs [55, 45, 41, 69, 8, 54, 48], or learned by imposing a smoothness constraint over time [33, 25, 67, 75, 73, 57, 22, 17, 50].”
Deep Learning on Graphs: A Survey (2018, unknown): “Dynamic GCN [29] applied an LSTM to gather the results of GCNs from different time slices in dynamic networks to capture both the spatial and temporal graph information.”
Relational Representation Learning for Dynamic (Knowledge) Graphs: A Survey (2019, methodology): “…approach where M is the GCN proposed in [59] and the RNN is a standard LSTM. Narayan and Roe [166] also use this approach with M being the GCN proposed in [174] and the RNN being a standard LSTM. Manessi et al. [155] modify this approach slightly by (mainly) adding skip-connections in the GCN part.”