DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification
Jun Wu,Jingrui He,Jiejun Xu +2 more
- pp 406-415
Reads0
Chats0
TLDR
A generic degree-specific graph neural network named DEMO-Net motivated by Weisfeiler-Lehman graph isomorphism test that recursively identifies 1-hop neighborhood structures is proposed and two multi-task learning methods: degree- specific weight and hashing functions for graph convolution are designed.Abstract:
Graph data widely exist in many high-impact applications. Inspired by the success of deep learning in grid-structured data, graph neural network models have been proposed to learn powerful node-level or graph-level representation. However, most of the existing graph neural networks suffer from the following limitations: (1) there is limited analysis regarding the graph convolution properties, such as seed-oriented, degree-aware and order-free; (2) the node's degreespecific graph structure is not explicitly expressed in graph convolution for distinguishing structure-aware node neighborhoods; (3) the theoretical explanation regarding the graph-level pooling schemes is unclear. To address these problems, we propose a generic degree-specific graph neural network named DEMO-Net motivated by Weisfeiler-Lehman graph isomorphism test that recursively identifies 1-hop neighborhood structures. In order to explicitly capture the graph topology integrated with node attributes, we argue that graph convolution should have three properties: seed-oriented, degree-aware, order-free. To this end, we propose multi-task graph convolution where each task represents node representation learning for nodes with a specific degree value, thus leading to preserving the degreespecific graph structure. In particular, we design two multi-task learning methods: degree-specific weight and hashing functions for graph convolution. In addition, we propose a novel graph-level pooling/readout scheme for learning graph representation provably lying in a degree-specific Hilbert kernel space. The experimental results on several node and graph classification benchmark data sets demonstrate the effectiveness and efficiency of our proposed DEMO-Net over state-of-the-art graph neural network models.read more
Citations
More filters
Proceedings ArticleDOI
AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
TL;DR: This paper proposes an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN), which extracts the specific and common embeddings from node features, topological structures, and their combinations simultaneously, and uses the attention mechanism to learn adaptive importance weights of the embeddeddings.
Posted Content
Data Augmentation for Graph Neural Networks
TL;DR: This work shows that neural edge predictors can effectively encode class-homophilic structure to promote intra- class edges and demote inter-class edges in given graph structure, and introduces the GAug graph data augmentation framework, which leverages these insights to improve performance in GNN-based node classification via edge prediction.
Posted Content
Computing Graph Neural Networks: A Survey from Algorithms to Accelerators
TL;DR: A review of the field of GNNs is presented from the perspective of computing, and an in-depth analysis of current software and hardware acceleration schemes is provided, from which a hardware-software, graph-aware, and communication-centric vision for GNN accelerators is distilled.
Proceedings ArticleDOI
AM-GCN: Adaptive Multi-channel Graph Convolutional Networks
TL;DR: In this article, an adaptive multi-channel graph convolutional networks for semi-supervised classification (AM-GCN) is proposed, where the specific and common embeddings from node features, topological structures, and their combinations simultaneously, and use the attention mechanism to learn adaptive importance weights of the embedding.
Proceedings ArticleDOI
Investigating and Mitigating Degree-Related Biases in Graph Convoltuional Networks
Xianfeng Tang,Huaxiu Yao,Yiwei Sun,Yiqi Wang,Jiliang Tang,Charu C. Aggarwal,Prasenjit Mitra,Suhang Wang +7 more
TL;DR: A novel Self-Supervised-Learning Degree-Specific GCN (SL-DSGCN) is developed that not only outperforms state-of-the-art self-training/self-supervised-learning GCN methods, but also improves GCN accuracy dramatically for low-degree nodes.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
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.
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.
Proceedings ArticleDOI
Graph Attention Networks
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.