Heterogeneous Attributed Network Embedding with Graph Convolutional Networks

Yueyang, Wang; Duan, Ziheng; Liao, Binbing; Wu, Fei; Zhuang, Yueting

doi:10.1609/aaai.v33i01.330110061

Cited by 30 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HetGNN [33] and HeGAN [8] incorporate bi-directional LSTM, attention mechanism, and generative adversarial networks (GAN) for heterogeneous network embedding. These methods rely on domain knowledge to choose the valuable metapaths, whereas there also exist several methods [26,32] which do not require meta-path selection. However, HANE [26] transforms various types of nodes with different attributes into a uniform space, which cannot distinguish the diversity of edges between nodes.…”

Section: Related Workmentioning

confidence: 99%

“…These methods rely on domain knowledge to choose the valuable metapaths, whereas there also exist several methods [26,32] which do not require meta-path selection. However, HANE [26] transforms various types of nodes with different attributes into a uniform space, which cannot distinguish the diversity of edges between nodes. GTN [32] needs explicit products of candidate adjacency matrices and requires additional memory space and computing resources.…”

Section: Related Workmentioning

confidence: 99%

“…GCNs have recently been widely used in heterogeneous network embedding and have achieved great success [12,25,26,32]. Nevertheless, these methods all need to train a large number of parameters as well as a long training time, which is inefficient when dealing with large-scale networks.…”

Section: Fast Random Projection Embeddingmentioning

confidence: 99%

See 2 more Smart Citations

Fast Attributed Multiplex Heterogeneous Network Embedding

Liu

Huang²,

et al. 2020

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

View full text Add to dashboard Cite

In recent years, heterogeneous network representation learning has attracted considerable attentions with the consideration of multiple node types. However, most of them ignore the rich set of network attributes (attributed network) and different types of relations (multiplex network), which can hardly recognize the multimodal contextual signals across different relations. While a handful of network embedding techniques are developed for attributed multiplex heterogeneous networks, they are significantly limited to the scalability issue on large-scale network data, due to their heavy computation and memory cost. In this work, we propose a Fast Attributed Multiplex heterogeneous network Embedding framework (FAME) for large-scale network data, by mapping the units from different modalities (i.e., network topological structures, various node features and relations) into the same latent space in an efficient way. Our FAME is an integrative architecture with the scalable spectral transformation and sparse random projection, to automatically preserve both attribute semantics and multi-type relations in the learned embeddings. Extensive experiments on four real-world datasets with various network analytical tasks, demonstrate that FAME achieves both effectiveness and significant efficiency over state-of-the-art baselines. The source code is available at: https://github.com/ZhijunLiu95/FAME. CCS CONCEPTS • Mathematics of computing → Graph algorithms; • Computing methodologies → Learning latent representations.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Fast Attributed Multiplex Heterogeneous Network Embedding

Liu

Huang²,

et al. 2020

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

View full text Add to dashboard Cite

show abstract

“…References [23]- [25] integrate meta paths and attention mechanism to capture the semantic information in HNs. Reference [26] separates the same type of nodes from Heterogeneous Information Networks (HINs), then aggregates the heterogeneous neighbors.…”

Section: B Neural Model On Networkmentioning

confidence: 99%

WMGCN: Weighted Meta-Graph Based Graph Convolutional Networks for Representation Learning in Heterogeneous Networks

et al. 2020

View full text Add to dashboard Cite

Network embedding has been an effective tool to analyze heterogeneous networks (HNs) by representing nodes in a low-dimensional space. Although many recent methods have been proposed for representation learning of HNs, there is still much room for improvement. Random walks based methods are currently popular methods to learn network embedding; however, they are random and limited by the length of sampled walks, and have difficulty capturing network structural information. Some recent researches proposed using meta paths to express the sample relationship in HNs. Another popular graph learning model, the graph convolutional network (GCN) is known to be capable of better exploitation of network topology, but the current design of GCN is intended for homogenous networks. This paper proposes a novel combination of meta-graph and graph convolution, the meta-graph based graph convolutional networks (MGCN). To fully capture the complex long semantic information, MGCN utilizes different meta-graphs in HNs. As different meta-graphs express different semantic relationships, MGCN learns the weights of different meta-graphs to make up for the loss of semantics when applying GCN. In addition, we improve the current convolution design by adding node self-significance. To validate our model in learning feature representation, we present comprehensive experiments on four real-world datasets and two representation tasks: classification and link prediction. WMGCN's representations can improve accuracy scores by up to around 10% in comparison to other popular representation learning models. What's more, WMGCN'feature learning outperforms other popular baselines. The experimental results clearly show our model is superior over other state-of-the-art representation learning algorithms.INDEX TERMS Heterogeneous network, weighted meta-graph, graph convolutional network, representation learning.

show abstract

“…Relations between two entities are easily captured by a graph [25,26], wherein a collection of pairwise edges (either directed or undirected) encapsulates the relational structure (e.g., friendship relations between two people on a social network [32,1]). Moreover, heterogeneous graphs [31,37] are used to capture relationship structures between entities of multiple "types" (e.g., a bibliographic network [9] between nodes of type author, paper, venue, etc.). However, when the number of types is restricted to two (say, "left" and "right"), and relations exist only across (and not among) them, we resort to a bipartite graph [20] (e.g., an author-paper bibliography network).…”

Section: Introductionmentioning

confidence: 99%

The CAT SET on the MAT: Cross Attention for Set Matching in Bipartite Hypergraphs

Sharma¹,

Singh²,

Devi³

et al. 2021

Preprint

View full text Add to dashboard Cite

Usual relations between entities could be captured using graphs; but those of a higher-order -more so between two different types of entities (which we term "left" and "right") -calls for a "bipartite hypergraph". For example, given a left set of symptoms and right set of diseases, the relation between a set subset of symptoms (that a patient experiences at a given point of time) and a subset of diseases (that he/she might be diagnosed with) could be well-represented using a bipartite hyperedge. The state-of-the-art in embedding nodes of a hypergraph is based on learning the self-attention structure between node-pairs from a hyperedge. In the present work, given a bipartite hypergraph, we aim at capturing relations between node pairs from the cross-product between the left and right hyperedges, and term it a "cross-attention" (CAT) based model. More precisely, we pose "bipartite hyperedge link prediction" as a set-matching (SETMAT) problem and propose a novel neural network architecture called CATSETMAT for the same. We perform extensive experiments on multiple bipartite hypergraph datasets to show the superior performance of CATSETMAT, which we compare with multiple techniques from the state-of-the-art. Our results also elucidate information flow in self-and cross-attention scenarios.Preprint. Under review.

show abstract

Heterogeneous Attributed Network Embedding with Graph Convolutional Networks

Cited by 30 publications

References 0 publications

Fast Attributed Multiplex Heterogeneous Network Embedding

Fast Attributed Multiplex Heterogeneous Network Embedding

WMGCN: Weighted Meta-Graph Based Graph Convolutional Networks for Representation Learning in Heterogeneous Networks

The CAT SET on the MAT: Cross Attention for Set Matching in Bipartite Hypergraphs

Contact Info

Product

Resources

About