Co-Regularized Deep Multi-Network Embedding

Ni, Jingchao; Chang, Shiyu; Liu, Xiao; Cheng, Wei; Chen, Haifeng; Xu, Daolin; Zhang, Xiang

doi:10.1145/3178876.3186113

Cited by 56 publications

(40 citation statements)

References 28 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A ij ŷ i −ŷ j 2 , which directly regulates the predictions of connected nodes to be similar [8], [9], [22], [23]. The assumption could also be implicitly implemented by iteratively propagating node embeddings through the graph so that connected nodes obtain close embeddings and are predicted similarly [3], [7], [10], [11]. Here, λ is a hyperparameter to balance the two terms.…”

Section: Graph-based Learningmentioning

confidence: 99%

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Feng

Tang

et al. 2021

IEEE Trans. Knowl. Data Eng.

131

View full text Add to dashboard Cite

Recent efforts show that neural networks are vulnerable to small but intentional perturbations on input features in visual classification tasks. Due to the additional consideration of connections between examples (e.g., articles with citation link tend to be in the same class), graph neural networks could be more sensitive to the perturbations, since the perturbations from connected examples exacerbate the impact on a target example. Adversarial Training (AT), a dynamic regularization technique, can resist the worst-case perturbations on input features and is a promising choice to improve model robustness and generalization. However, existing AT methods focus on standard classification, being less effective when training models on graph since it does not model the impact from connected examples. In this work, we explore adversarial training on graph, aiming to improve the robustness and generalization of models learned on graph. We propose Graph Adversarial Training (GraphAT), which takes the impact from connected examples into account when learning to construct and resist perturbations. We give a general formulation of GraphAT, which can be seen as a dynamic regularization scheme based on the graph structure. To demonstrate the utility of GraphAT, we employ it on a state-of-the-art graph neural network model -Graph Convolutional Network (GCN). We conduct experiments on two citation graphs (Citeseer and Cora) and a knowledge graph (NELL), verifying the effectiveness of GraphAT which outperforms normal training on GCN by 4.51% in node classification accuracy. Codes are available via: https://github.com/fulifeng/GraphAT.

show abstract

Section: Graph-based Learningmentioning

confidence: 99%

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Feng

Tang

et al. 2021

IEEE Trans. Knowl. Data Eng.

131

View full text Add to dashboard Cite

show abstract

“…HAN (Wang et al 2019) employed graph attention network (Veličković et al 2017) on each graph, and then applied the attention mechanism to merge the node representations learned from each graph by considering the importance of each graph. However, the existing methods either require labels for training (Wang et al 2019;Qu et al 2017;Schlichtkrull et al 2018), or overlook the node attributes (Liu et al 2017;Xu et al 2017;Li et al 2018;Shi et al 2018;Zhang et al 2018a;Ni et al 2018;Chu et al 2019). Most recently, Ma et al (2019) proposed a graph convolutional network (GCN) based method called mGCN, which is not only unsupervised, but also naturally incorporates the node attributes by using GCNs.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Attributed Multiplex Network Embedding

Park

Kim

Han

et al. 2020

AAAI

155

116

View full text Add to dashboard Cite

Nodes in a multiplex network are connected by multiple types of relations. However, most existing network embedding methods assume that only a single type of relation exists between nodes. Even for those that consider the multiplexity of a network, they overlook node attributes, resort to node labels for training, and fail to model the global properties of a graph. We present a simple yet effective unsupervised network embedding method for attributed multiplex network called DMGI, inspired by Deep Graph Infomax (DGI) that maximizes the mutual information between local patches of a graph, and the global representation of the entire graph. We devise a systematic way to jointly integrate the node embeddings from multiple graphs by introducing 1) the consensus regularization framework that minimizes the disagreements among the relation-type specific node embeddings, and 2) the universal discriminator that discriminates true samples regardless of the relation types. We also show that the attention mechanism infers the importance of each relation type, and thus can be useful for filtering unnecessary relation types as a preprocessing step. Extensive experiments on various downstream tasks demonstrate that DMGI outperforms the state-of-the-art methods, even though DMGI is fully unsupervised.

show abstract

“…More recently, there is another line of HIN embedding study, decomposing based methods. These methods learn node embeddings by decomposing HIN semantics into projected metrics with different relation spaces (such as PME [8], HEER [30] and RHINE [20]), or decomposing HINs into cross-network relationships in different sub-networks (such as AMN [26], DME [23] and AspEm [29]). However, these methods are not suitable for HINs that have a large number of types, since the metrics projecting or sub-networks decomposing are conducted in type-pair-specific level, leading in the exponential growth of spaces with respect to the number of types.…”

Section: Related Workmentioning

confidence: 99%

An Adaptive Embedding Framework for Heterogeneous Information Networks

Chen

Ding

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Heterogeneous information networks (HINs) have been ubiquitous in the real-world. HIN embeddings, which encode various information of the networks into low-dimensional vectors, can facilitate a wide range of applications on graph-structured data. Existing HIN embedding methods include random walk based methods that may not fully utilize the edge semantics and knowledge graph embedding methods that restrict the expression ability of topological information. In this paper, we propose a novel adaptive embedding framework, which integrates these two kinds of methods to preserve both topological information and relational information. By incorporating an assistant knowledge graph embedding model, the proposed framework performs efficient biased random walk under the guidance of edge semantics. Meanwhile, the short and long dependency information can be adaptively preserved for diverse networks. Furthermore, a patient joint training strategy is proposed to make the framework flexible and adapt to different assistant knowledge graph embedding models. Extensive experiments on five real-world datasets demonstrate that the proposed method can adaptively sample node contexts and outperforms several stateof-the-art methods for node classification and link prediction tasks. CCS CONCEPTS • Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Co-Regularized Deep Multi-Network Embedding

Cited by 56 publications

References 28 publications

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure

Unsupervised Attributed Multiplex Network Embedding

An Adaptive Embedding Framework for Heterogeneous Information Networks

Contact Info

Product

Resources

About