skip to main content
10.1145/3488560.3498470acmconferencesArticle/Chapter ViewAbstractPublication PageswsdmConference Proceedingsconference-collections
research-article

Directed Network Embedding with Virtual Negative Edges

Published: 15 February 2022 Publication History

Abstract

The directed network embedding problem is to represent the nodes in a given directed network as embeddings (i.e., low-dimensional vectors) that preserve the asymmetric relationships between nodes. While a number of approaches have been developed for this problem, we point out that existing approaches commonly face difficulties in accurately preserving asymmetric proximities between nodes in a sparse network containing a large number of low out- and in-degree nodes. In this paper, we focus on addressing this intrinsic difficulty caused by the lack of information. We first introduce the concept of virtual negative edges (VNEs), which represent latent negative relationships between nodes. Based on the concept, we propose a novel DIrected NE approach with VIrtual Negative Edges, named as DIVINE. DIVINE carefully decides the number and locations of VNEs to be added to the input network. Once VNEs are added, DIVINE learns embeddings by exploiting both the signs and directions of edges. Our experiments on four real-world directed networks demonstrate that adding VNEs alleviates the lack of information about low-degree nodes, thereby enabling DIVINE to yield high-quality embeddings that accurately capture asymmetric proximities between nodes. Specifically, the embeddings obtained by DIVINE lead to up to 10.16% more accurate link prediction, compared to those obtained by state-of-the-art competitors.

Supplementary Material

MP4 File (WSDM22-fp516.mp4)
Presentation video (short version) of the paper "Directed Network Embedding with Virtual Negative Edges"

References

[1]
Samin Aref, Ly Dinh, Rezvaneh Rezapour, and Jana Diesner. 2020. Multilevel structural evaluation of signed directed social networks based on balance theory. Scientific Reports, Vol. 10, 1 (2020), 1--12.
[2]
Samin Aref and Mark C. Wilson. 2019. Balance and frustration in signed networks. J. Complex Networks, Vol. 7, 2 (2019), 163--189.
[3]
Shaosheng Cao, Wei Lu, and Qiongkai Xu. 2015. GraRep: Learning Graph Representations with Global Structural Information. In Proc. of the ACM International Conference on Information and Knowledge Management (ACM CIKM). 891--900.
[4]
Dorwin Cartwright and Frank Harary. 1956. Structural balance: a generalization of Heider's theory. Psychological Review, Vol. 63, 5 (1956), 277--293.
[5]
Peng Cui, Xiao Wang, Jian Pei, and Wenwu Zhu. 2019. A Survey on Network Embedding. IEEE Trans. Knowl. Data Eng., Vol. 31, 5 (2019), 833--852.
[6]
Aditya Grover and Jure Leskovec. 2016. Node2vec: Scalable Feature Learning for Networks. In Proc. of the ACM International Conference on Knowledge Discovery and Data Mining (ACM KDD) . 855--864.
[7]
William L. Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive Representation Learning on Large Graphs. In Proc. of the Annual Conference. on Neural Information Processing Systems (NeurIPS). 1024--1034.
[8]
James A Hanley and Barbara J McNeil. 1982. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, Vol. 143, 1 (1982), 29--36.
[9]
Fritz Heider. 1946. Attitudes and cognitive organization. The Journal of psychology, Vol. 21, 1 (1946), 107--112.
[10]
Leo Katz. 1953. A new status index derived from sociometric analysis. Psychometrika, Vol. 18, 1 (1953), 39--43.
[11]
Megha Khosla, Jurek Leonhardt, Wolfgang Nejdl, and Avishek Anand. 2019. Node Representation Learning for Directed Graphs. In Proc. of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Vol. 11906. 395--411.
[12]
Junghwan Kim, Haekyu Park, Ji-Eun Lee, and U. Kang. 2018. SIDE: Representation Learning in Signed Directed Networks. In Proc. of The Web Conference (WWW) . 509--518.
[13]
Thomas N. Kipf and Max Welling. 2016. Variational Graph Auto-Encoders. In Proc. NeurIPS Workshop Bayesian Deep Learning . 1--3.
[14]
Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proc. of the International Conference on Learning Representations (ICLR) .
[15]
Johannes Klicpera, Stefan Weißenberger, and Stephan Gü nnemann. 2019. Diffusion Improves Graph Learning. In Proc. of the Annual Conference. on Neural Information Processing Systems (NeurIPS). 13333--13345.
[16]
Jé rô me Kunegis, Julia Preusse, and Felix Schwagereit. 2013. What is the added value of negative links in online social networks?. In Proc. of The Web Conference (WWW). 727--736.
[17]
Wonchang Lee, Yeon-Chang Lee, Dongwon Lee, and Sang-Wook Kim. 2021. Look Before You Leap: Confirming Edge Signs in Random Walk with Restart for Personalized Node Ranking in Signed Networks. In Proc. of the ACM International Conference on Research & Development in Information Retrieval (ACM SIGIR) . 143--152.
[18]
Yeon-Chang Lee, Nayoun Seo, Kyungsik Han, and Sang-Wook Kim. 2020. ASiNE: Adversarial Signed Network Embedding. In Proc. of the ACM International Conference on Research & Development in Information Retrieval (ACM SIGIR) . 609--618.
[19]
Jure Leskovec, Daniel P. Huttenlocher, and Jon M. Kleinberg. 2010. Predicting positive and negative links in online social networks. In Proc. of The Web Conference (WWW). 641--650.
[20]
Jundong Li, Harsh Dani, Xia Hu, Jiliang Tang, Yi Chang, and Huan Liu. 2017. Attributed Network Embedding for Learning in a Dynamic Environment. In Proc. of the ACM International Conference on Information and Knowledge Management (ACM CIKM). 387--396.
[21]
David Liben-Nowell and Jon M. Kleinberg. 2003. The link prediction problem for social networks. In Proc. of the ACM International Conference on Information and Knowledge Management (ACM CIKM). 556--559.
[22]
Mingdong Ou, Peng Cui, Jian Pei, Ziwei Zhang, and Wenwu Zhu. 2016. Asymmetric Transitivity Preserving Graph Embedding. In Proc. of the ACM International Conference on Knowledge Discovery and Data Mining (ACM KDD) . 1105--1114.
[23]
Christopher C Paige and Michael A Saunders. 1981. Towards a generalized singular value decomposition. SIAM J. Numer. Anal., Vol. 18, 3 (1981), 398--405.
[24]
Rong Pan, Yunhong Zhou, Bin Cao, Nathan Nan Liu, Rajan M. Lukose, Martin Scholz, and Qiang Yang. 2008. One-Class Collaborative Filtering. In Proc. of the IEEE International Conference on Data Mining (IEEE ICDM). 502--511.
[25]
Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. DeepWalk: online learning of social representations. In Proc. of the ACM International Conference on Knowledge Discovery and Data Mining (ACM KDD) . 701--710.
[26]
Ruslan Salakhutdinov and Geoffrey E. Hinton. 2009. Semantic hashing. Int. J. Approx. Reason., Vol. 50, 7 (2009), 969--978.
[27]
Guillaume Salha, Stratis Limnios, Romain Hennequin, Viet-Anh Tran, and Michalis Vazirgiannis. 2019. Gravity-Inspired Graph Autoencoders for Directed Link Prediction. In Proc. of the ACM International Conference on Information and Knowledge Management (ACM CIKM). 589--598.
[28]
Kijung Shin, Jinhong Jung, Lee Sael, and U Kang. 2015. BEAR: Block Elimination Approach for Random Walk with Restart on Large Graphs. In Proc. of the ACM SIGMOD International Conference on Management of Data (ACM SIGMOD) . 1571--1585.
[29]
Han Hee Song, Tae Won Cho, Vacha Dave, Yin Zhang, and Lili Qiu. 2009. Scalable proximity estimation and link prediction in online social networks. In Proc. of the ACM SIGCOMM Internet Measurement Conference (IMC). 322--335.
[30]
Jiankai Sun, Bortik Bandyopadhyay, Armin Bashizade, Jiongqian Liang, P. Sadayappan, and Srinivasan Parthasarathy. 2019. ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation. In Proc. of the AAAI International Conference on Artificial Intelligence (AAAI) . 265--272.
[31]
Jiliang Tang, Yi Chang, Charu C. Aggarwal, and Huan Liu. 2016. A Survey of Signed Network Mining in Social Media. ACM Comput. Surv., Vol. 49, 3 (2016), 42:1--42:37.
[32]
Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan, and Qiaozhu Mei. 2015. LINE: Large-scale Information Network Embedding. In Proc. of The Web Conference (WWW) . 1067--1077.
[33]
Zekun Tong, Yuxuan Liang, Changsheng Sun, Xinke Li, David S. Rosenblum, and Andrew Lim. 2020. Digraph Inception Convolutional Networks. In Proc. of the Annual Conference on Neural Information Processing Systems (NeurIPS) .
[34]
Daixin Wang, Peng Cui, and Wenwu Zhu. 2016. Structural Deep Network Embedding. In Proc. of the ACM International Conference on Knowledge Discovery and Data Mining (ACM KDD). 1225--1234.
[35]
Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, and Shiqiang Yang. 2017. Community Preserving Network Embedding. In Proc. of the AAAI International Conference on Artificial Intelligence (AAAI). 203--209.
[36]
Pinghua Xu, Wenbin Hu, Jia Wu, Weiwei Liu, Bo Du, and Jian Yang. 2019. Social Trust Network Embedding. In Proc. of the IEEE International Conference on Data Mining (IEEE ICDM). 678--687.
[37]
Shuhan Yuan, Xintao Wu, and Yang Xiang. 2017. SNE: Signed Network Embedding. In Proc. of the Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD). 183--195.
[38]
Daokun Zhang, Jie Yin, Xingquan Zhu, and Chengqi Zhang. 2020. Network Representation Learning: A Survey. IEEE Trans. Big Data, Vol. 6, 1 (2020), 3--28.
[39]
Zhen Zhang, Hongxia Yang, Jiajun Bu, Sheng Zhou, Pinggang Yu, Jianwei Zhang, Martin Ester, and Can Wang. 2018. ANRL: Attributed Network Representation Learning via Deep Neural Networks. In Proc. of the International Joint Conference on Artificial Intelligence (IJCAI) . 3155--3161.
[40]
Tong Zhao, Yozen Liu, Leonardo Neves, Oliver Woodford, Meng Jiang, and Neil Shah. 2021. Data Augmentation for Graph Neural Networks. Proc. of the AAAI International Conference on Artificial Intelligence (AAAI) .
[41]
Chang Zhou, Yuqiong Liu, Xiaofei Liu, Zhongyi Liu, and Jun Gao. 2017. Scalable Graph Embedding for Asymmetric Proximity. In Proc. of the AAAI International Conference on Artificial Intelligence (AAAI). 2942--2948.
[42]
Shenghuo Zhu, Kai Yu, Yun Chi, and Yihong Gong. 2007. Combining content and link for classification using matrix factorization. In Proc. of the ACM International Conference on Research & Development in Information Retrieval (ACM SIGIR). 487--494.

Cited By

View all
  • (2024)Trustworthiness-Driven Graph Convolutional Networks for Signed Network EmbeddingACM Transactions on Knowledge Discovery from Data10.1145/368527918:9(1-26)Online publication date: 14-Oct-2024
  • (2024)MERLIN: Multimodal & Multilingual Embedding for Recommendations at Large-scale via Item AssociationsProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3680106(4914-4921)Online publication date: 21-Oct-2024
  • (2024)PolarDSN: An Inductive Approach to Learning the Evolution of Network Polarization in Dynamic Signed NetworksProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679654(1099-1109)Online publication date: 21-Oct-2024
  • Show More Cited By

Index Terms

  1. Directed Network Embedding with Virtual Negative Edges

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining
    February 2022
    1690 pages
    ISBN:9781450391320
    DOI:10.1145/3488560
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Sponsors

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 15 February 2022

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. directed networks
    2. network embedding
    3. virtual negative edges

    Qualifiers

    • Research-article

    Funding Sources

    • Research fund of Hanyang University
    • National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT)
    • Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT)

    Conference

    WSDM '22

    Acceptance Rates

    Overall Acceptance Rate 498 of 2,863 submissions, 17%

    Upcoming Conference

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)48
    • Downloads (Last 6 weeks)1
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2024)Trustworthiness-Driven Graph Convolutional Networks for Signed Network EmbeddingACM Transactions on Knowledge Discovery from Data10.1145/368527918:9(1-26)Online publication date: 14-Oct-2024
    • (2024)MERLIN: Multimodal & Multilingual Embedding for Recommendations at Large-scale via Item AssociationsProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3680106(4914-4921)Online publication date: 21-Oct-2024
    • (2024)PolarDSN: An Inductive Approach to Learning the Evolution of Network Polarization in Dynamic Signed NetworksProceedings of the 33rd ACM International Conference on Information and Knowledge Management10.1145/3627673.3679654(1099-1109)Online publication date: 21-Oct-2024
    • (2024)Random-Walk-Based or Similarity-Based Methods, Which is Better for Directed Graph Embedding?2024 IEEE International Conference on Big Data and Smart Computing (BigComp)10.1109/BigComp60711.2024.00022(83-89)Online publication date: 18-Feb-2024
    • (2024)Network embedding based on DepDist contractionApplied Network Science10.1007/s41109-024-00639-x9:1Online publication date: 2-Jul-2024
    • (2023)ELTRA: An Embedding Method based on Learning-to-Rank to Preserve Asymmetric Information in Directed GraphsProceedings of the 32nd ACM International Conference on Information and Knowledge Management10.1145/3583780.3614862(2116-2125)Online publication date: 21-Oct-2023
    • (2023)Disentangling Degree-related Biases and Interest for Out-of-Distribution Generalized Directed Network EmbeddingProceedings of the ACM Web Conference 202310.1145/3543507.3583271(231-239)Online publication date: 30-Apr-2023
    • (2023)TrustSGCN: Learning Trustworthiness on Edge Signs for Effective Signed Graph Convolutional NetworksProceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3539618.3592075(2451-2455)Online publication date: 19-Jul-2023
    • (2022)Phishing URL DetectionProceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security10.1145/3548606.3560615(1769-1782)Online publication date: 7-Nov-2022
    • (2022)THOR: Self-Supervised Temporal Knowledge Graph Embedding via Three-Tower Graph Convolutional Networks2022 IEEE International Conference on Data Mining (ICDM)10.1109/ICDM54844.2022.00127(1035-1040)Online publication date: Nov-2022

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media