Learning Vertex Representations for Bipartite Networks

Gao, Ming; He, Xiangnan; Chen, Leihui; Liu, Tingting; Zhang, Jinglin; Zhou, Aoying

doi:10.1109/tkde.2020.2979980

Cited by 21 publications

(16 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HNE models that adopt the bipartite strategy, initially split heterogeneous networks into multiple bipartite networks, by sampling both explicit and implicit links between the vertices [12], [13], [17]. They then apply different optimization strategies to learn node embeddings.…”

Section: Heterogeneous Network Embeddingmentioning

confidence: 99%

DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks

Imran¹,

Yin²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Modeling heterogeneity by extraction and exploitation of high-order information from heterogeneous information networks (HINs) has been attracting immense research attention in recent times. Such heterogeneous network embedding (HNE) methods effectively harness the heterogeneity of small-scale HINs. However, in the real world, the size of HINs grow exponentially with the continuous introduction of new nodes and different types of links, making it a billion-scale network. Learning node embeddings on such HINs creates a performance bottleneck for existing HNE methods that are commonly centralized, i.e., complete data and the model are both on a single machine. To address large-scale HNE tasks with strong efficiency and effectiveness guarantee, we present Decentralized Embedding Framework for Heterogeneous Information Network (DeHIN) in this paper. In DeHIN, we generate a distributed parallel pipeline that utilizes hypergraphs in order to infuse parallelization into the HNE task. DeHIN presents a context preserving partition mechanism that innovatively formulates a large HIN as a hypergraph, whose hyperedges connect semantically similar nodes. Our framework then adopts a decentralized strategy to efficiently partition HINs by adopting a tree-like pipeline. Then, each resulting subnetwork is assigned to a distributed worker, which employs the deep information maximization theorem to locally learn node embeddings from the partition it receives. We further devise a novel embedding alignment scheme to precisely project independently learned node embeddings from all subnetworks onto a common vector space, thus allowing for downstream tasks like link prediction and node classification. As shown from our experimental results, DeHIN significantly improves the efficiency and accuracy of existing HNE models as well as outperforms the large-scale graph embedding frameworks by efficiently scaling up to large-scale HINs.

show abstract

Section: Heterogeneous Network Embeddingmentioning

confidence: 99%

DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks

Imran¹,

Yin²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Different from multiplex bipartite networks, simple bipartite networks contain two types of nodes and a single type of edges. Several bipartite network embedding methods have been proposed, including BiNE [11,12], BGNN [16], BiANE [19], FOBE and HOBE [29]. BiNE first performs biased random walks to generate node sequences and then uses a joint optimization strategy to preserve both explicit and implicit information within bipartite networks simultaneously.…”

Section: Related Workmentioning

confidence: 99%

Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks

Xue

Yang

Rajan

et al. 2021

Preprint

View full text Add to dashboard Cite

A bipartite network is a graph structure where nodes are from two distinct domains and only inter-domain interactions exist as edges. A large number of network embedding methods exist to learn vectorial node representations from general graphs with both homogeneous and heterogeneous node and edge types, including some that can specifically model the distinct properties of bipartite networks. However, these methods are inadequate to model multiplex bipartite networks (e.g., in e-commerce), that have multiple types of interactions (e.g., click, inquiry, and buy) and node attributes. Most real-world multiplex bipartite networks are also sparse and have imbalanced node distributions that are challenging to model. In this paper, we develop an unsupervised Dual HyperGraph Convolutional Network (DualHGCN) model that scalably transforms the multiplex bipartite network into two sets of homogeneous hypergraphs and uses spectral hypergraph convolutional operators, along with intra-and inter-message passing strategies to promote information exchange within and across domains, to learn effective node embeddings. We benchmark DualHGCN using four real-world datasets on link prediction and node classification tasks. Our extensive experiments demonstrate that DualHGCN significantly outperforms state-of-the-art methods, and is robust to varying sparsity levels and imbalanced node distributions. CCS CONCEPTS• Computing methodologies → Neural networks.

show abstract

“…We use the same division in IGMC [42] for ML-100K. Following experimental settings in the previous work [8], we split Wikipedia into two datasets, i.e., Wiki (5:5) and Wiki (4:6). The training/test ratios of these two datasets are 5:5 and 4:6, respectively.…”

Section: Data Preprocessingmentioning

confidence: 99%

“…Although they work pretty well in the settings of homogeneous and heterogeneous graphs, most of them are not tailored for modeling bipartite graphs. As a result, they are suboptimal to learn bipartite graph embedding [7,8]. To remedy such a problem, several studies have been specifically proposed for modeling bipartite graphs.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bipartite Graph Embedding via Mutual Information Maximization

Cao

Lin

Guo

et al. 2020

Preprint

View full text Add to dashboard Cite

Bipartite graph embedding has recently attracted much attention due to the fact that bipartite graphs are widely used in various application domains. Most previous methods, which adopt random walk-based or reconstruction-based objectives, are typically effective to learn local graph structures. However, the global properties of bipartite graph, including community structures of homogeneous nodes and long-range dependencies of heterogeneous nodes, are not well preserved. In this paper, we propose a bipartite graph embedding called BiGI to capture such global properties by introducing a novel local-global infomax objective. Specifically, BiGI first generates a global representation which is composed of two prototype representations. BiGI then encodes sampled edges as local representations via the proposed subgraph-level attention mechanism. Through maximizing the mutual information between local and global representations, BiGI enables nodes in bipartite graph to be globally relevant. Our model is evaluated on various benchmark datasets for the tasks of top-K recommendation and link prediction. Extensive experiments demonstrate that BiGI achieves consistent and significant improvements over state-of-the-art baselines. Detailed analyses verify the high effectiveness of modeling the global properties of bipartite graph. CCS CONCEPTS• Information systems → Data mining; • Computing methodologies → Neural networks.

show abstract

Learning Vertex Representations for Bipartite Networks

Cited by 21 publications

References 47 publications

DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks

DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks

Multiplex Bipartite Network Embedding using Dual Hypergraph Convolutional Networks

Bipartite Graph Embedding via Mutual Information Maximization

Contact Info

Product

Resources

About