node2coords: Graph Representation Learning with Wasserstein Barycenters

• URL: http://arxiv.org/abs/2007.16056v2
• Date: Sun, 3 Jan 2021 18:17:47 GMT
• Title: node2coords: Graph Representation Learning with Wasserstein Barycenters
• Authors: Effrosyni Simou, Dorina Thanou and Pascal Frossard
• Abstract summary: We introduce node2coords, a representation learning algorithm for graphs. It learns simultaneously a low-dimensional space and coordinates for the nodes in that space. Experimental results demonstrate that the representations learned with node2coords are interpretable.
• Score: 59.07120857271367
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods do not learn representations that can be interpreted in a straightforward way and that are robust to perturbations to the graph structure. In this work, we address these two limitations by proposing node2coords, a representation learning algorithm for graphs, which learns simultaneously a low-dimensional space and coordinates for the nodes in that space. The patterns that span the low dimensional space reveal the graph's most important structural information. The coordinates of the nodes reveal the proximity of their local structure to the graph structural patterns. In order to measure this proximity by taking into account the underlying graph, we propose to use Wasserstein distances. We introduce an autoencoder that employs a linear layer in the encoder and a novel Wasserstein barycentric layer at the decoder. Node connectivity descriptors, that capture the local structure of the nodes, are passed through the encoder to learn the small set of graph structural patterns. In the decoder, the node connectivity descriptors are reconstructed as Wasserstein barycenters of the graph structural patterns. The optimal weights for the barycenter representation of a node's connectivity descriptor correspond to the coordinates of that node in the low-dimensional space. Experimental results demonstrate that the representations learned with node2coords are interpretable, lead to node embeddings that are stable to perturbations of the graph structure and achieve competitive or superior results compared to state-of-the-art methods in node classification.

Related papers

• Recovering Missing Node Features with Local Structure-based Embeddings [34.79801041888119]
  We present a framework to recover completely missing node features for a set of graphs. Our approach incorporates prior information from both graph topology and existing nodal values.
  arXiv  Detail & Related papers  (2023-09-16T18:23:14Z)
• PA-GM: Position-Aware Learning of Embedding Networks for Deep Graph Matching [14.713628231555223]
  We introduce a novel end-to-end neural network that can map the linear assignment problem into a high-dimensional space. Our model constructs the anchor set for the relative position of nodes. It then aggregates the feature information of the target node and each anchor node based on a measure of relative position.
  arXiv  Detail & Related papers  (2023-01-05T06:54:21Z)
• Local Graph Embeddings Based on Neighbors Degree Frequency of Nodes [0.0]
  We propose a strategy for graph machine learning and network analysis by defining certain local features and vector representations of nodes. By extending the notion of the degree of a node via Breath-First Search, a general family of bf centrality functions is defined. We show that centrality and closeness can be learned by applying deep learning to these local features.
  arXiv  Detail & Related papers  (2022-07-30T07:07:30Z)
• LiftPool: Lifting-based Graph Pooling for Hierarchical Graph Representation Learning [53.176603566951016]
  We propose an enhanced three-stage method via lifting, named LiftPool, to improve hierarchical graph representation. For each node to be removed, its local information is obtained by subtracting the global information aggregated from its neighboring preserved nodes. Evaluations on benchmark graph datasets show that LiftPool substantially outperforms the state-of-the-art graph pooling methods in the task of graph classification.
  arXiv  Detail & Related papers  (2022-04-27T12:38:02Z)
• Learning Sparse Graphs with a Core-periphery Structure [14.112444998191698]
  We propose a generative model for data associated with core-periphery structured networks. We infer a sparse graph and nodal core scores that induce dense (sparse) connections in core parts of the network.
  arXiv  Detail & Related papers  (2021-10-08T10:41:30Z)
• Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical [85.0376670244522]
  We investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. We develop a Star-shaped Reasoning Graph Network (S-RGN) to exploit more powerful and flexible capacity. We also develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity.
  arXiv  Detail & Related papers  (2021-09-06T03:16:56Z)
• COLOGNE: Coordinated Local Graph Neighborhood Sampling [1.6498361958317633]
  replacing discrete unordered objects such as graph nodes by real-valued vectors is at the heart of many approaches to learning from graph data. We address the problem of learning discrete node embeddings such that the coordinates of the node vector representations are graph nodes. This opens the door to designing interpretable machine learning algorithms for graphs as all attributes originally present in the nodes are preserved.
  arXiv  Detail & Related papers  (2021-02-09T11:39:06Z)
• Spectral Embedding of Graph Networks [76.27138343125985]
  We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure. The embedding is based on a generalized graph Laplacian, whose eigenvectors compactly capture both network structure and neighborhood proximity in a single representation.
  arXiv  Detail & Related papers  (2020-09-30T04:59:10Z)
• Graph Pooling with Node Proximity for Hierarchical Representation Learning [80.62181998314547]
  We propose a novel graph pooling strategy that leverages node proximity to improve the hierarchical representation learning of graph data with their multi-hop topology. Results show that the proposed graph pooling strategy is able to achieve state-of-the-art performance on a collection of public graph classification benchmark datasets.
  arXiv  Detail & Related papers  (2020-06-19T13:09:44Z)
• Graph Inference Learning for Semi-supervised Classification [50.55765399527556]
  We propose a Graph Inference Learning framework to boost the performance of semi-supervised node classification. For learning the inference process, we introduce meta-optimization on structure relations from training nodes to validation nodes. Comprehensive evaluations on four benchmark datasets demonstrate the superiority of our proposed GIL when compared against state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-01-17T02:52:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.