An Attention-based Collaboration Framework for Multi-View Network Representation Learning

Qu, Meng; Tang, Jian; Shang, Jingbo; Ren, Xiang; Zhang, Ming; Han, Jiawei

doi:10.1145/3132847.3133021

Cited by 140 publications

(103 citation statements)

References 37 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…PMNE [22] proposes three methods to project a multiplex network into a continuous vector space. MVE [30] embeds networks with multiple views in a single collaborated embedding using attention mechanism. MNE [43] uses one common embedding and several additional embeddings of each edge type for each node, which are jointly learned by a unified network embedding model.…”

Section: Related Workmentioning

confidence: 99%

Representation Learning for Attributed Multiplex Heterogeneous Network

Cen

Zou

Zhang

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

373

200

View full text Add to dashboard Cite

Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks. Many real-world networks consist of billions of nodes and edges of multiple types, and each node is associated with different attributes. In this paper, we formalize the problem of embedding learning for the Attributed Multiplex Heterogeneous Network and propose a unified framework to address this problem. The framework supports both transductive and inductive learning. We also give the theoretical analysis of the proposed framework, showing its connection with previous works and proving its better expressiveness. We conduct systematical evaluations for the proposed framework on four different genres of challenging datasets: Amazon, YouTube, Twitter, and Alibaba 1 . Experimental results demonstrate that with the learned embeddings from the proposed framework, we can achieve statistically significant improvements (e.g., 5.99-28.23% lift by F1 scores; p ≪ 0.01, t−test) over previous state-of-the-art methods for link prediction.The framework has also been successfully deployed on the recommendation system of a worldwide leading e-commerce company, Alibaba Group. Results of the offline A/B tests on product recommendation further confirm the effectiveness and efficiency of the framework in practice.

show abstract

Section: Related Workmentioning

confidence: 99%

Representation Learning for Attributed Multiplex Heterogeneous Network

Cen

Zou

Zhang

et al. 2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

373

200

View full text Add to dashboard Cite

show abstract

“…Thus we omit SDNE for brevity. Note multi-view network embedding method [30] cannot be applied on these datasets since the cross-network relationships are many-to-many.…”

Section: Track: Socialmentioning

confidence: 99%

“…The multi-view network embedding method [30] may be the most relevant work, but, as discussed before in Sec. 1, it cannot be applied when the cross-network relationship is many-to-many, weighted and incomplete, as shown in Fig.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Co-Regularized Deep Multi-Network Embedding

Chang²,

Liu

et al. 2018

Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18

View full text Add to dashboard Cite

Network embedding aims to learn a low-dimensional vector representation for each node in the social and information networks, with the constraint to preserve network structures. Most existing methods focus on single network embedding, ignoring the relationship between multiple networks. In many real-world applications, however, multiple networks may contain complementary information, which can lead to further re ned node embeddings. Thus, in this paper, we propose a novel multi-network embedding method, DMNE. DMNE is exible. It allows di erent networks to have different sizes, to be (un)weighted and (un)directed. It leverages multiple networks via cross-network relationships between nodes in different networks, which may form many-to-many node mappings, and be associated with weights. To model the non-linearity of the network data, we develop DMNE to have a new deep learning architecture, which coordinates multiple neural networks (one for each input network data) with a co-regularized loss function. With multiple layers of non-linear mappings, DMNE progressively transforms each input network to a highly non-linear latent space, and in the meantime, adapts di erent spaces to each other through a co-regularized learning schema. Extensive experimental results on real-life datasets demonstrate the e ectiveness of our method.

show abstract

“…The research in network embedding has thus far focused primarily on social, biological, and information networks [10]- [17]. Such networks differ significantly from road networks in terms of, e.g., structure, semantics, size, node degree, network diameter, and the amount of attribute information available.…”

Section: Introductionmentioning

confidence: 99%

On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network

Jepsen

Jensen

Nielsen

et al. 2018

2018 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Road networks are a type of spatial network, where edges may be associated with qualitative information such as road type and speed limit. Unfortunately, such information is often incomplete; for instance, OpenStreetMap only has speed limits for 13% of all Danish road segments. This is problematic for analysis tasks that rely on such information for machine learning. To enable machine learning in such circumstances, one may consider the application of network embedding methods to extract structural information from the network. However, these methods have so far mostly been used in the context of social networks, which differ significantly from road networks in terms of, e.g., node degree and level of homophily (which are key to the performance of many network embedding methods).We analyze the use of network embedding methods, specifically node2vec, for learning road segment embeddings in road networks. Due to the often limited availability of information on other relevant road characteristics, the analysis focuses on leveraging the spatial network structure. Our results suggest that network embedding methods can indeed be used for deriving relevant network features (that may, e.g, be used for predicting speed limits), but that the qualities of the embeddings differ from embeddings for social networks.

show abstract

An Attention-based Collaboration Framework for Multi-View Network Representation Learning

Cited by 140 publications

References 37 publications

Representation Learning for Attributed Multiplex Heterogeneous Network

Representation Learning for Attributed Multiplex Heterogeneous Network

Co-Regularized Deep Multi-Network Embedding

On Network Embedding for Machine Learning on Road Networks: A Case Study on the Danish Road Network

Contact Info

Product

Resources

About