Open AccessPosted Content
Data Augmentation View on Graph Convolutional Network and the Proposal of Monte Carlo Graph Learning.
TL;DR: This work proposes a new graph learning paradigm -- Monte Carlo Graph Learning (MCGL), and re-analyze the reasons why the performance of GCN becomes worse when deepened too much: the main reason is the graph structure noise.
read more
Abstract: Today, there are two major understandings for graph convolutional networks, ie, in the spectral and spatial domain But both lack transparency In this work, we introduce a new understanding for it -- data augmentation, which is more transparent than the previous understandings Inspired by it, we propose a new graph learning paradigm -- Monte Carlo Graph Learning (MCGL) The core idea of MCGL contains: (1) Data augmentation: propagate the labels of the training set through the graph structure and expand the training set; (2) Model training: use the expanded training set to train traditional classifiers We use synthetic datasets to compare the strengths of MCGL and graph convolutional operation on clean graphs In addition, we show that MCGL's tolerance to graph structure noise is weaker than GCN on noisy graphs (four real-world datasets) Moreover, inspired by MCGL, we re-analyze the reasons why the performance of GCN becomes worse when deepened too much: rather than the mainstream view of over-smoothing, we argue that the main reason is the graph structure noise, and experimentally verify our view The code is available at this https URL
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Null Model-Based Data Augmentation for Graph Classification
Zhuoyuan Wang,Jinhuan Wang,Yalu Shan,Shanqing Yu,Xiao-Ke Xu,Qi Xuan,Guanrong Chen +6 more
TL;DR: Null model-based data augmentation for graph classification improves performance by preserving topological features and capturing latent information.
1
LoyalDE: Improving the performance of Graph Neural Networks with loyal node discovery and emphasis
TL;DR: Li et al. as discussed by the authors proposed a model-agnostic hot-plugging training strategy, which can discover potential nodes with high loyalty to expand the training set, and then emphasize nodes of high loyalty during model training to improve performance.
•Posted Content
Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification
TL;DR: Wang et al. as mentioned in this paper proposed an attentional integrating model to weighted sum the hidden node embeddings encoded by these GCNs into the final node embedding, which improves the classification accuracy with a clear margin (+2.5% - +84.2%).
Data Augmentation for Graph Convolutional Network on Semi-supervised Classification.
Zhengzheng Tang,Ziyue Qiao,Xuehai Hong,Yang Wang,Fayaz Ali Dharejo,Yuanchun Zhou,Yi Du +6 more
- 23 Aug 2021
TL;DR: Wang et al. as discussed by the authors proposed an attentional integrating model to weighted sum the hidden node embeddings encoded by these GCNs into the final node embedding, which improves the classification accuracy with a clear margin (+2.5%++84.2%) than the original GCN.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Posted Content
Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf,Max Welling +1 more
TL;DR: A scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs which outperforms related methods by a significant margin.
22.7K
Graph Attention Networks
Petar Veličković,Guillem Cucurull,Arantxa Casanova,Adriana Romero,Pietro Liò,Yoshua Bengio +5 more
- 15 Feb 2018
TL;DR: Graph Attention Networks (GATs) as mentioned in this paper leverage masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.
•Proceedings Article
Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf,Max Welling +1 more
- 09 Sep 2016
TL;DR: In this paper, a scalable approach for semi-supervised learning on graph-structured data is presented based on an efficient variant of convolutional neural networks which operate directly on graphs.
•Posted Content
Inductive Representation Learning on Large Graphs
TL;DR: GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.
11.9K