Bayesian Graph Convolutional Neural Networks for Semi-Supervised Classification

Zhang, Yingxue; Pal, Soumyasundar; Coates, Mark; Üstebay, Deniz

doi:10.1609/aaai.v33i01.33015829

Cited by 153 publications

(106 citation statements)

References 14 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…MoNet [38] shows that various non-Euclidean CNN methods including GCN are its particular instances. Other related works include GraphSAGE [25], graph attention networks [51], attention-based graph neural network [47], graph partition neural networks [36], FastGCN [16], dual graph convolutional neural network [65], stochastic GCN [17], Bayesian GCN [58], deep graph infomax [50], Lanc-zosNet [37], etc. We refer readers to two comprehensive surveys [60,62] for more discussions.…”

Section: Related Workmentioning

confidence: 99%

Label Efficient Semi-Supervised Learning via Graph Filtering

Li¹,

Liu

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

145

View full text Add to dashboard Cite

Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance. However, existing graph-based methods either are limited in their ability to jointly model graph structures and data features, such as the classical label propagation methods, or require a considerable amount of labeled data for training and validation due to high model complexity, such as the recent neural-network-based methods. In this paper, we address label efficient semi-supervised learning from a graph filtering perspective. Specifically, we propose a graph filtering framework that injects graph similarity into data features by taking them as signals on the graph and applying a low-pass graph filter to extract useful data representations for classification, where label efficiency can be achieved by conveniently adjusting the strength of the graph filter. Interestingly, this framework unifies two seemingly very different methods -label propagation and graph convolutional networks. Revisiting them under the graph filtering framework leads to new insights that improve their modeling capabilities and reduce model complexity. Experiments on various semi-supervised classification tasks on four citation networks and one knowledge graph and one semi-supervised regression task for zero-shot image recognition validate our findings and proposals.

show abstract

Section: Related Workmentioning

confidence: 99%

Label Efficient Semi-Supervised Learning via Graph Filtering

Li¹,

Liu

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

145

View full text Add to dashboard Cite

show abstract

“…Early works [18]- [20] used label propagation and random walks on the user-item interaction graph to derive similarity scores for user-item pairs. With the emerging field in Graph Neural Networks (GNNs) [21]- [24], more recent works have started to apply graph neural networks [11], [12], [25]. Graph Convolutional Matrix Completion (GCMC) [25] treats the recommendation problem as a matrix completion task and employs a graph convolution autoencoder.…”

Section: B Graph-based Recommendationmentioning

confidence: 99%

Multi-graph Convolution Collaborative Filtering

Sun

Zhang

et al. 2019

2019 IEEE International Conference on Data Mining (ICDM)

Self Cite

120

View full text Add to dashboard Cite

Personalized recommendation is ubiquitous, playing an important role in many online services. Substantial research has been dedicated to learning vector representations of users and items with the goal of predicting a user's preference for an item based on the similarity of the representations. Techniques range from classic matrix factorization to more recent deep learning based methods. However, we argue that existing methods do not make full use of the information that is available from user-item interaction data and the similarities between user pairs and item pairs. In this work, we develop a graph convolution-based recommendation framework, named Multi-Graph Convolution Collaborative Filtering (Multi-GCCF), which explicitly incorporates multiple graphs in the embedding learning process. Multi-GCCF not only expressively models the high-order information via a bipartite user-item interaction graph, but also integrates the proximal information by building and processing user-user and item-item graphs. Furthermore, we consider the intrinsic difference between user nodes and item nodes when performing graph convolution on the bipartite graph. We conduct extensive experiments on four publicly accessible benchmarks, showing significant improvements relative to several state-ofthe-art collaborative filtering and graph neural network-based recommendation models. Further experiments quantitatively verify the effectiveness of each component of our proposed model and demonstrate that the learned embeddings capture the important relationship structure.

show abstract

“…图对抗攻击对原始图的结构或节点特征进行轻微扰动, 以改变网络对特定节点的预测 (参见文献 [79]). 在对抗防御方面, Bayes 图卷积网络 [80] 通过将观测到的图看作一族含参随机图的实现, 提升了神经网络在攻击下的鲁棒性. 目前这一领域已有一些研究工作 (参见文献 [79,81,82]), 但仍有待进一步探索.…”

Section: 图对抗攻防unclassified

Graph neural network

Bai¹,

Liu²,

Chicheng³

et al. 2020

Sci. Sin.-Math.

View full text Add to dashboard Cite

如果 v i 与 v j 有边连}, 这里 (i, j) = (j, i); • l vi : v i 的特征向量, 简记为 l i ; 表 1 模型分类分类模型空间方法 GoriGNN [9, 10] 、LGNN [15] 、GGS-NN [16] 、GPNN [17] 、GGT-NN [18] 、FGNN [19] 谱方法 SpectralGCN [20] 、ChebNets [21] 、GCN [22] 、CayleyNets [23] 图生成基于自编码器: SDNE [24] 、VGAE [25] 、DVNE [26] 基于生成对抗网络: GraphGAN [27] 、MolGAN [28] 、GraphSGAN [29] 其他生成方法: GraphRNN [30] 、DGNN [31]

show abstract

Bayesian Graph Convolutional Neural Networks for Semi-Supervised Classification

Cited by 153 publications

References 14 publications

Label Efficient Semi-Supervised Learning via Graph Filtering

Label Efficient Semi-Supervised Learning via Graph Filtering

Multi-graph Convolution Collaborative Filtering

Graph neural network

Contact Info

Product

Resources

About