Dual GNNs: Graph Neural Network Learning with Limited Supervision
- URL: http://arxiv.org/abs/2106.15755v1
- Date: Tue, 29 Jun 2021 23:52:25 GMT
- Title: Dual GNNs: Graph Neural Network Learning with Limited Supervision
- Authors: Abdullah Alchihabi, Yuhong Guo
- Abstract summary: We propose a novel Dual GNN learning framework to address this challenge task.
By integrating the two modules in a dual GNN learning framework, we perform joint learning in an end-to-end fashion.
- Score: 33.770877823910176
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Graph Neural Networks (GNNs) require a relatively large number of labeled
nodes and a reliable/uncorrupted graph connectivity structure in order to
obtain good performance on the semi-supervised node classification task. The
performance of GNNs can degrade significantly as the number of labeled nodes
decreases or the graph connectivity structure is corrupted by adversarial
attacks or due to noises in data measurement /collection. Therefore, it is
important to develop GNN models that are able to achieve good performance when
there is limited supervision knowledge -- a few labeled nodes and noisy graph
structures. In this paper, we propose a novel Dual GNN learning framework to
address this challenge task. The proposed framework has two GNN based node
prediction modules. The primary module uses the input graph structure to induce
regular node embeddings and predictions with a regular GNN baseline, while the
auxiliary module constructs a new graph structure through fine-grained spectral
clusterings and learns new node embeddings and predictions. By integrating the
two modules in a dual GNN learning framework, we perform joint learning in an
end-to-end fashion. This general framework can be applied on many GNN baseline
models. The experimental results validate that the proposed dual GNN framework
can greatly outperform the GNN baseline methods when the labeled nodes are
scarce and the graph connectivity structure is noisy.
Related papers
- Geodesic Graph Neural Network for Efficient Graph Representation
Learning [34.047527874184134]
We propose an efficient GNN framework called Geodesic GNN (GDGNN)
It injects conditional relationships between nodes into the model without labeling.
Conditioned on the geodesic representations, GDGNN is able to generate node, link, and graph representations that carry much richer structural information than plain GNNs.
arXiv Detail & Related papers (2022-10-06T02:02:35Z) - A Variational Edge Partition Model for Supervised Graph Representation
Learning [51.30365677476971]
This paper introduces a graph generative process to model how the observed edges are generated by aggregating the node interactions over a set of overlapping node communities.
We partition each edge into the summation of multiple community-specific weighted edges and use them to define community-specific GNNs.
A variational inference framework is proposed to jointly learn a GNN based inference network that partitions the edges into different communities, these community-specific GNNs, and a GNN based predictor that combines community-specific GNNs for the end classification task.
arXiv Detail & Related papers (2022-02-07T14:37:50Z) - Hierarchical Message-Passing Graph Neural Networks [12.207978823927386]
We propose a novel Hierarchical Message-passing Graph Neural Networks framework.
Key idea is generating a hierarchical structure that re-organises all nodes in a flat graph into multi-level super graphs.
We present the first model to implement this framework, termed Hierarchical Community-aware Graph Neural Network (HC-GNN)
arXiv Detail & Related papers (2020-09-08T13:11:07Z) - Distance Encoding: Design Provably More Powerful Neural Networks for
Graph Representation Learning [63.97983530843762]
Graph Neural Networks (GNNs) have achieved great success in graph representation learning.
GNNs generate identical representations for graph substructures that may in fact be very different.
More powerful GNNs, proposed recently by mimicking higher-order tests, are inefficient as they cannot sparsity of underlying graph structure.
We propose Distance Depiction (DE) as a new class of graph representation learning.
arXiv Detail & Related papers (2020-08-31T23:15:40Z) - GPT-GNN: Generative Pre-Training of Graph Neural Networks [93.35945182085948]
Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data.
We present the GPT-GNN framework to initialize GNNs by generative pre-training.
We show that GPT-GNN significantly outperforms state-of-the-art GNN models without pre-training by up to 9.1% across various downstream tasks.
arXiv Detail & Related papers (2020-06-27T20:12:33Z) - Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs [95.63153473559865]
Graph Neural Networks (GNNs) are emerging machine learning models on graphs.
Most existing GNN models in practice are shallow and essentially feature-centric.
We show empirically and analytically that the existing shallow GNNs cannot preserve graph structures well.
We propose Eigen-GNN, a plug-in module to boost GNNs ability in preserving graph structures.
arXiv Detail & Related papers (2020-06-08T02:47:38Z) - Binarized Graph Neural Network [65.20589262811677]
We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters.
Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches.
Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
arXiv Detail & Related papers (2020-04-19T09:43:14Z) - A Collective Learning Framework to Boost GNN Expressiveness [25.394456460032625]
We consider the task of inductive node classification using Graph Neural Networks (GNNs) in supervised and semi-supervised settings.
We propose a general collective learning approach to increase the representation power of any existing GNN.
We evaluate performance on five real-world network datasets and demonstrate consistent, significant improvement in node classification accuracy.
arXiv Detail & Related papers (2020-03-26T22:07:28Z) - Bilinear Graph Neural Network with Neighbor Interactions [106.80781016591577]
Graph Neural Network (GNN) is a powerful model to learn representations and make predictions on graph data.
We propose a new graph convolution operator, which augments the weighted sum with pairwise interactions of the representations of neighbor nodes.
We term this framework as Bilinear Graph Neural Network (BGNN), which improves GNN representation ability with bilinear interactions between neighbor nodes.
arXiv Detail & Related papers (2020-02-10T06:43:38Z)
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.