skip to main content
10.1145/3583780.3614862acmconferencesArticle/Chapter ViewAbstractPublication PagescikmConference Proceedingsconference-collections
research-article

ELTRA: An Embedding Method based on Learning-to-Rank to Preserve Asymmetric Information in Directed Graphs

Published: 21 October 2023 Publication History

Abstract

Double-vector embedding methods capture the asymmetric information in directed graphs first, and then preserve them in the embedding space by providingtwo latent vectors, i.e., source and target, per node. Although these methods are known to besuperior to the single-vector ones (i.e., providing asingle latent vector per node), wepoint out their three drawbacks as inability to preserve asymmetry on NU-paths, inability to preserve global nodes similarity, and impairing in/out-degree distributions. To address these, we first proposeCRW, anovel similarity measure for graphs that considers contributions ofboth in-links and out-links in similarity computation,without ignoring their directions. Then, we proposeELTRA, aneffective double-vector embedding method to preserve asymmetric information in directed graphs. ELTRA computesasymmetry preserving proximity scores (AP-scores) by employing CRW in which the contribution of out-links and in-links in similarity computation isupgraded anddowngraded, respectively. Then, for every node u, ELTRA selects its top-tclosest nodes based on AP-scores andconforms theranks of their corresponding target vectors w.r.t u's source vector in the embedding space to theiroriginal ranks. Our extensive experimental results withseven real-world datasets andsixteen embedding methods show that (1) CRWsignificantly outperforms Katz and RWR in computing nodes similarity in graphs, (2) ELTRAoutperforms the existing state-of-the-art methods in graph reconstruction, link prediction, and node classification tasks.

References

[1]
Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, and Hang Li. 2007. Learning to Rank: from Pairwise Approach to Listwise Approach. In Proceedings of the 24th International Conference on Machine Learning, ICML. 129--136.
[2]
Peizhe Cheng, Shuaiqiang Wang, Jun Ma, Jiankai Sun, and Hui Xiong. 2017. Learning to Recommend Accurate and Diverse Items. In Proceedings of the 26th International Conference on World Wide Web, WWW. 183--192.
[3]
Quanyu Dai, Xiao Shen, Liang Zhang, Qiang Li, and Dan Wang. 2019. Adversarial Training Methods for Network Embedding. In Proceedings of the 28th International Conference on World Wide Web, WWW. 329--339.
[4]
Gene H. Golub and Charles F. Van Loan. 2013. Matrix Computations. Johns Hopkins Univ. Press, 4th Edition.
[5]
Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable Feature Learning for Networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD. 855--864.
[6]
Masoud Reyhani Hamedani and Sang-Wook Kim. 2021a. AdaSim: A Recursive Similarity Measure in Graphs. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management, CIKM. 1528--1537.
[7]
Masoud Reyhani Hamedani and Sang-Wook Kim. 2021b. JacSim*: An Effective and Efficient Solution to the Pairwise Normalization Problem in SimRank. IEEE Access, Vol. 9 (2021), 146038--146049.
[8]
Masoud Reyhani Hamedani, Jin-Su Ryu, and Sang-Wook Kim. 2023. GELTOR: A Graph Embedding Method based on Listwise Learning to Rank. In Proceedings of the ACM Web Conference 2023, WWW. 6--16.
[9]
Jiawei Han, Micheline Kamber, and Jian Pei. 2006. Data Mining: Concepts and Techniques, Second Edition. Morgan Kaufmann, San Francisco.
[10]
Mingliang Hou, Jing Ren, Da Zhang, Xiangjie Kong, Dongyu Zhang, and Feng Xia. 2020. Network Embedding: Taxonomies, Frameworks and Applications. Computer Science Review, Vol. 38 (2020), 100296.
[11]
Swayambhoo Jain, Akshay Soni, Nikolay Laptev, and Yashar Mehdad. 2017. Rank-to-Engage: New Listwise Approaches to Maximize Engagement. arxiv: 1702.07798 [stat.ML]
[12]
Kalervo Järvelin and Jaana Kekäläinen. 2002. Cumulated Gain-Based Evaluation of IR Techniques. ACM Transactions on Information Systems, Vol. 20, 4 (2002), 422--446.
[13]
Leo Katz. 1953. A New Status Index Derived from Sociometric Analysis. Psychometrika, Vol. 18, 1 (1953), 39--43.
[14]
Moein Khajehnejad. 2019. SimNet: Similarity-Based Network Embeddings with Mean Commute Time. Plos ONE, Vol. 14, 8 (2019), 1102--1110.
[15]
Megha Khosla, Jurek Leonhardt, Wolfgang Nejdl, and Avishek Anandm. 2019. Node Representation Learning for Directed Graphs. In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database, ECML-PKDD. 395--411.
[16]
Junghwan Kim, Haekyu Park, Ji-Eun Lee, and U Kang. 2018. SIDE: Representation Learning in Signed Directed Networks. In Proceedings of the International Conference on World Wide Web, WWW. 509--518.
[17]
Yanyan Lan, Tie-Yan Liu, Zhiming Ma, and Hang Li. 2009. Generalization Analysis of Listwise Learning-to-Rank Algorithms. In Proceedings of the 26nd International Conference on Machine Learning, ICML. 577--584.
[18]
Yeon-Chang Lee, Nayoun Seo, and Sang-Wook Kim. 2020. Are Negative Links Really Beneficial to Network Embedding?: In-Depth Analysis and Interesting Results. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management, CIKM. 2113--2116.
[19]
Jure Leskovec, Jon Kleinberg, and Christos Faloutsos. 2005. Graphs over Time: Densification Laws, Shrinking Diameters and Possible Explanations. In Proceedings of the 11th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD. 177--187.
[20]
Dmitry Lizorkin, Pavel Velikhov, Maxim Grinev, and Denis Turdakov. 2008. Accuracy Estimate and Optimization Techniques for SimRank Computation. In Proceedings of the VLDB Endowment. 422--433.
[21]
Tiancheng Lou, Jie Tang, John Hopcroft, Zhanpeng Fang, and Xiaowen Ding. 2013. Learning to predict Reciprocity and Triadic Closure in Social Networks. ACM Transactions on Knowledge Discovery from Data, Vol. 7, 2 (2013), 1--25.
[22]
Christopher.D. Manning, Prabhakar Raghavan, and Hinrich Schutze. 2008. Introduction to Information Retrieval. Cambridge University Press.
[23]
John I. Marden. 1995. Analyzing and Modeling Rank Data. Chapman and Hall/CRC.
[24]
Donna Katzman McClish. 1989. Analyzing a portion of the ROC curve. Medical Decision Making, Vol. 9, 3 (1989), 190--195.
[25]
Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. Efficient Estimation of Word Representations in Vector Space. arxiv: 1301.3781 [cs.CL]
[26]
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013b. Distributed Representations of Words and Phrases and Their Compositionality. In Proceedings of the 26th International Conference on Neural Information Processing Systems, NIPS. 3111--3119.
[27]
Cameron Musco and Christopher Musco. 2015. Randomized Block Krylov Methods for Stronger and Faster Approximate Singular Value Decomposition. In Proceedings of the Advances in Neural Information Processing Systems, NeurIPS. 1396--1404.
[28]
Mingdong Ou, Peng Cui, Jian Pei, and Ziwei Zhang. 2016. Asymmetric Transitivity Preserving Graph Embedding. In Proceedings of the 22nd ACM International Conference on Knowledge Discovery and Data Mining, KDD. 1105--1114.
[29]
Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. DeepWalk: Online Learning of Social Representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD. 701--710.
[30]
Tao Qin, Xu-Dong Zhang, Ming-Feng Tsai, De-Sheng Wang, Tie-Yan Liu, and Hang Li. 2008. Query-Level Loss Functions for Information Retrieval. The Journal of Information Processing and Management, Vol. 44, 2 (2008), 838--855.
[31]
Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, and Jie Tang. 2018. Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec. In Proceedings of the 11st ACM International Conference on Web Search and Data Mining, WSDM. 459--467.
[32]
Y. Saad. 2003. Iterative Methods for Sparse Linear Systems. Society for Industrial and Applied Mathematics, Philadelphia, PA, USA.
[33]
Guillaume Salha, Stratis Limnios, Romain Hennequin, Viet Anh Tran, and Michalis Vazirgiannis. 2019. Gravity-Inspired Graph Autoencoders for Directed Link Prediction. In Proceedings of the 28th ACM Conference on Information and Knowledge Management, CIKM. 589--598.
[34]
Jiankai Sun, Bortik Bandyopadhyay, Armin Bashizade, Jiongqian Liang, P. Sadayappan, and Srinivasan Parthasarathy. 2019. ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence, AAAI. 265--272.
[35]
Thibaut Thonet, Yagmur Gizem Cinar, Eric Gaussier, Minghan Li, and Jean-Michel Renders. 2022. Listwise Learning to Rank Based on Approximate Rank Indicators. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI. 8494--8502.
[36]
Hanghang Tong, Christos Faloutsos, and Jia yu Pan. 2006. Fast Random Walk with Restart and Its Applications. In Proceedings of the 6th IEEE International Conference on Data Mining, ICDM. 613--622.
[37]
Anton Tsitsulin, Davide Mottin, Panagiotis Karras, and Emmanuel Müller. 2018. VERSE: Versatile Graph Embeddings from Similarity Measures. In Proceedings of the International Conference on World Wide Web, WWW. 539--548.
[38]
Anton Tsitsulin, Marina Munkhoeva, Davide Mottin, Panagiotis Karras, Ivan Oseledets, and Emmanuel Müller. 2021. FREDE: Anytime Graph Embeddings. Proceedings of the VLDB Endowment, Vol. 14, 6 (2021), 1102--1110.
[39]
Hongwei Wang, Jia Wang, Jialin Wang, Miao Zhao, Weinan Zhang, Fuzheng Zhang, Xing Xie, and Minyi Guo1. 2018. GraphGAN: Graph Representation Learning with Generative Adversarial Nets. In Proceedings of the 32nd AAAI Conference on Artificial Intelligence, AAAI. 2508--2515.
[40]
Fen Xia, Tie-Yan Liu, and Hang Li. 2009. Statistical Consistency of Top-k Ranking. In Proceedings of the 22th International Conference on Neural Information Processing Systems, NIPS. 2098--2106.
[41]
Fen Xia, Tie-Yan Liu, Jue Wang, and Wensheng Zhang Hang Li. 2008. Listwise Approach to Learning to Rank: Theory and Algorithm. In Proceedings of the 25th International Conference on Machine Learning, ICML. 1192--1199.
[42]
Renchi Yang, Jieming Shi, Xiaokui Xiao, Yin Yang, and Sourav Bhowmick. 2020. Homogeneous Network Embedding for Massive Graphs via Reweighted Personalized PageRank. Proceedings of the VLDB Endowment, Vol. 13, 5 (2020), 670--683.
[43]
Yuan Yin and Zhewei We. 2019. Scalable Graph Embeddings via Sparse Transpose Proximities. In Proceedings of the 25nd ACM International Conference on Knowledge Discovery and Data Mining, KDD. 1429--1437.
[44]
Hyunsik Yoo, Yeon-Chang Lee, Kijung Shin, and Sang-Wook Kim. 2022. Directed Network Embedding with Virtual Negative Edges. In Proceedings of the 15th ACM International Conference on Web Search and Data Mining, WSDM. 1291--1299.
[45]
Hyunsik Yoo, Yeon-Chang Lee, Kijung Shin, and Sang-Wook Kim. 2023. Disentangling Degree-related Biases and Interest for Out-of-Distribution Generalized Directed Network Embedding. In Proceedings of the ACM Web Conference 2023, WWW. 231--239.
[46]
Weiren Yu, Xuemin Lin, Wenjie Zhang, Jian Pei, and Julie A. McCann. 2019. Simrank*: Effective and Scalable Pairwise Similarity Search Based on Graph Topology. The VLDB Journal, Vol. 28, 3 (June 2019), 401--426.
[47]
Xingyi Zhang, Kun Xie, Sibo Wang, and Zengfeng Huang. 2021. Learning Based Proximity Matrix Factorization for Node Embedding. In Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD. 2243--2253.
[48]
Sheng Zhou, Xin Wang, Martin Ester, Bolang Li, Chen Ye, Zhen Zhang, Can Wang, and Jiajun Bu. 2021. Direction-Aware User Recommendation Based on Asymmetric Network Embedding. ACM Transactions on Information Systems, Vol. 40, 2 (2021), 1--23.
[49]
Xiaofeng Zhu and Diego Klabjan. 2020. Listwise Learning to Rank by Exploring Unique Ratings. In Proceedings of the 13th International Conference on Web Search and Data Mining, WSDM. 798--806.
[50]
Lovro ?ubelj and Marko Bajec. 2013. Model of Complex Networks based on Citation Dynamics. In Proceedings of the 22nd International Conference on World Wide Web, WWW Companion. 527--530.

Index Terms

  1. ELTRA: An Embedding Method based on Learning-to-Rank to Preserve Asymmetric Information in Directed Graphs

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Conferences
    CIKM '23: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
    October 2023
    5508 pages
    ISBN:9798400701245
    DOI:10.1145/3583780
    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 the author(s) 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: 21 October 2023

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. directed graph embedding
    2. learning-to-rank
    3. link-based similarity

    Qualifiers

    • Research-article

    Funding Sources

    • Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT)

    Conference

    CIKM '23
    Sponsor:

    Acceptance Rates

    Overall Acceptance Rate 1,861 of 8,427 submissions, 22%

    Upcoming Conference

    CIKM '25

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 120
      Total Downloads
    • Downloads (Last 12 months)70
    • Downloads (Last 6 weeks)11
    Reflects downloads up to 17 Jan 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Media

    Figures

    Other

    Tables

    Share

    Share

    Share this Publication link

    Share on social media