Dual-Primal Graph Convolutional Networks

By Federico Monti, Oleksandr Shchur, Aleksandar Bojchevski, Or Litany, Stephan Günnemann, Michael M. Bronstein. 2018

84 citations recorded by the source corpus.

In recent years, there has been a surge of interest in developing deep learning methods for non-Euclidean structured data such as graphs. In this paper, we propose Dual-Primal Graph CNN, a graph convolutional architecture that alternates convolution-like operations on the graph and its dual. Our approach allows to learn both vertex- and edge features and generalizes the previous graph attention (GAT) model. We provide extensive experimental validation showing state-of-the-art results on a variety of tasks tested on established graph benchmarks, including CORA and Citeseer citation networks as well as MovieLens, Flixter, Douban and Yahoo Music graph-guided recommender systems.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

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

In Information Systems

Citations in the corpus

Provably Powerful Graph Networks (2019, methodology): “onary functions that are applied to each node and its neighbours (e.g., Duvenaud et al. (2015); Atwood and Towsley (2016); Niepert et al. (2016); Hamilton et al. (2017b); Veliˇckovi ´c et al. (2017); Monti et al. (2018)). Many of these works were shown to be instances of the family of message passin”
HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs (2018, background): “Approaches that assign importance to nodes [46, 35, 45] have improved results on SSL. HyperGCN may be augmented with such approaches for even more improved performance.”
MeshCNN: a network with an edge (2019, methodology): “An interesting approach may be to process the edges using an attention mechanism [Monti et al. 2018].”
Relational Graph Attention Networks (2018, background): “A recent approach that began with Graph Attention Networks (GATs), applied attention mechanisms to graphs, and does not share these limitations (Veličković et al., 2017; Gong and Cheng, 2018; Zhang et al., 2018; Monti et al., 2018; Lee et al., 2018).”
Fake News Detection on Social Media using Geometric Deep Learning (2019, background): “Such spectral ﬁlters typically scale linearly with the graph size and can be generalized to higher order structures [25], dual graphs (edge ﬁlters) [26], and product graphs [24].”
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs (2019, methodology): “Inspired by the DPGCNN, in this paper, we propose a novel Relation-aware Dual-Graph Convolutional Network (RDGCN) to tackle the challenge of proper capturing and integration for relation information.”
Composition-based Multi-Relational Graph Convolutional Networks (2019, background): “Initial attempts at learning representations for relations in graphs (Monti et al., 2018; Beck et al., 2018) have shown some performance gains on tasks like node classiﬁcation and neural machine translation.”
Graph Wavelet Neural Network (2019, background): “Monti et al. (2018) alternated convolutions on vertices and edges, generalizing GAT and leading to better performance.”