Log In Sign Up

Edgeless-GNN: Unsupervised Inductive Edgeless Network Embedding

by   Yong-Min Shin, et al.

We study the problem of embedding edgeless nodes such as users who newly enter the underlying network, while using graph neural networks (GNNs) widely studied for effective representation learning of graphs thanks to its highly expressive capability via message passing. Our study is motivated by the fact that GNNs cannot be adopted for our problem since message passing to such edgeless nodes having no connections is impossible. To tackle this challenge, we propose Edgeless-GNN, a new framework that enables GNNs to generate node embeddings even for edgeless nodes through unsupervised inductive learning. Specifically, we utilize a k-nearest neighbor graph (kNNG) based on the similarity of node attributes to replace the GNN's computation graph defined by the neighborhood-based aggregation of each node. The known network structure is used to train model parameters, whereas a loss function is established in such a way that our model learns the network structure. For the edgeless nodes, we inductively infer embeddings by using edges via kNNG construction as a computation graph. By evaluating the performance of various downstream machine learning (ML) tasks, we empirically demonstrate that Edgeless-GNN consistently outperforms state-of-the-art methods of inductive network embedding. Our framework is GNN-model-agnostic; thus, GNN models can be appropriately chosen according to ones' needs and ML tasks.


page 2

page 3

page 5

page 6

page 8

page 10

page 11

page 12


Towards Expressive Graph Representation

Graph Neural Network (GNN) aggregates the neighborhood of each node into...

Revisiting Embeddings for Graph Neural Networks

Current graph representation learning techniques use Graph Neural Networ...

Unsupervised Joint k-node Graph Representations with Compositional Energy-Based Models

Existing Graph Neural Network (GNN) methods that learn inductive unsuper...

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

We target open-world feature extrapolation problem where the feature spa...

Persistent Message Passing

Graph neural networks (GNNs) are a powerful inductive bias for modelling...

Breaking the Limit of Graph Neural Networks by Improving the Assortativity of Graphs with Local Mixing Patterns

Graph neural networks (GNNs) have achieved tremendous success on multipl...

GNNAutoScale: Scalable and Expressive Graph Neural Networks via Historical Embeddings

We present GNNAutoScale (GAS), a framework for scaling arbitrary message...