skip to main content
10.1145/3488560.3498417acmconferencesArticle/Chapter ViewAbstractPublication PageswsdmConference Proceedingsconference-collections
research-article

Few-shot Link Prediction in Dynamic Networks

Published: 15 February 2022 Publication History

Abstract

Dynamic link prediction, which aims at forecasting future edges of a node in a dynamic network, is an important problem in network science and has a wide range of real-world applications. A key property of dynamic networks is that new nodes and links keep coming over time and these new nodes usually have only a few links at their arrivals. However, how to predict future links for these few-shot nodes in a dynamic network has not been well studied. Existing dynamic network representation learning methods were not specialized for few-shot scenarios and thus would lead to suboptimal performances. In this paper, we propose a novel model based on a meta-learning framework, dubbed as MetaDyGNN, for few-shot link prediction in dynamic networks. Specifically, we propose a meta-learner with hierarchical time interval-wise and node-wise adaptions to extract general knowledge behind this problem. We also design a simple and effective dynamic graph neural network (GNN) module to characterize the local structure of each node in meta-learning tasks. As a result, the learned general knowledge serves as model initializations, and can quickly adapt to new nodes with a fine-tuning process on only a few links. Experimental results show that our proposed MetaDyGNN significantly outperforms state-of-the-art methods on three publicly available datasets.

Supplementary Material

MP4 File (WSDM22-fp267.mp4)
This is the presentation video of the paper ''Few-shot Link Prediction in Dynamic Networks''. The video introduces the paper from introduction, model, experiments, and conclusions. In this paper, we propose a novel model based on a meta-learning framework, dubbed as MetaDyGNN, for few-shot link prediction in dynamic networks. Specifically, we propose a meta-learner with hierarchical time interval-wise and node-wise adaptions to extract general knowledge behind this problem. We also design a simple and effective dynamic graph neural network(GNN) module to characterize the local structure of each node in meta-learning tasks. As a result, the learned general knowledge serves as model initializations, and can quickly adapt to new nodes with a fine-tuning process on only a few links. Experimental results show that our proposed MetaDyGNN significantly outperforms state-of-the-art methods on three publicly available datasets.

References

[1]
Salomon Bochner. 1934. A theorem on Fourier-Stieltjes integrals. Bull. Amer. Math. Soc., Vol. 40, 4 (1934), 271--276.
[2]
Avishek Joey Bose, Ankit Jain, Piero Molino, and William L Hamilton. 2019. Meta-graph: Few shot link prediction via meta learning. arXiv preprint arXiv:1912.09867 (2019).
[3]
Jatin Chauhan, Deepak Nathani, and Manohar Kaul. 2020. Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures. arXiv preprint arXiv:2002.12815 (2020).
[4]
Aswathy Divakaran and Anuraj Mohan. 2019. Temporal link prediction: a survey. New Generation Computing (2019), 1--46.
[5]
Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of ICML . 1126--1135.
[6]
Palash Goyal, Sujit Rokka Chhetri, and Arquimedes Canedo. 2020. dyngraph2vec: Capturing network dynamics using dynamic graph representation learning. Knowledge-Based Systems, Vol. 187 (2020), 104816.
[7]
Zhichun Guo, Chuxu Zhang, Wenhao Yu, John Herr, Olaf Wiest, Meng Jiang, and Nitesh V Chawla. 2021. Few-Shot Graph Learning for Molecular Property Prediction. Proceedings of WWW (2021).
[8]
Ehsan Hajiramezanali, Arman Hasanzadeh, Nick Duffield, Krishna R Narayanan, Mingyuan Zhou, and Xiaoning Qian. 2019. Variational graph recurrent neural networks. arXiv preprint arXiv:1908.09710 (2019).
[9]
William L Hamilton, Rex Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. Proceedings of NeurIPS (2017).
[10]
Petter Holme and Jari Saram"aki. 2012. Temporal networks. Physics reports, Vol. 519, 3 (2012), 97--125.
[11]
Kexin Huang and Marinka Zitnik. 2020. Graph meta learning via local subgraphs. arXiv preprint arXiv:2006.07889 (2020).
[12]
Vassilis N Ioannidis, Da Zheng, and George Karypis. 2020. Few-shot link prediction via graph neural networks for covid-19 drug-repurposing. arXiv preprint arXiv:2007.10261 (2020).
[13]
Seyed Mehran Kazemi, Rishab Goel, Sepehr Eghbali, Janahan Ramanan, Jaspreet Sahota, Sanjay Thakur, Stella Wu, Cathal Smyth, Pascal Poupart, and Marcus Brubaker. 2019 a. Time2vec: Learning a vector representation of time. arXiv preprint arXiv:1907.05321 (2019).
[14]
Seyed Mehran Kazemi, Rishab Goel, Kshitij Jain, Ivan Kobyzev, Akshay Sethi, Peter Forsyth, and Pascal Poupart. 2019 b. Relational representation learning for dynamic (knowledge) graphs: A survey. arXiv preprint arXiv:1905.11485 (2019).
[15]
Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016).
[16]
Srijan Kumar, Xikun Zhang, and Jure Leskovec. 2019. Predicting dynamic embedding trajectory in temporal interaction networks. In Proceedings of SIGKDD . 1269--1278.
[17]
Hoyeop Lee, Jinbae Im, Seongwon Jang, Hyunsouk Cho, and Sehee Chung. 2019. Melu: Meta-learned user preference estimator for cold-start recommendation. In Proceedings of SIGKDD. 1073--1082.
[18]
Peng Liu, Lemei Zhang, and Jon Atle Gulla. 2019. Real-time social recommendation based on graph embedding and temporal context. International Journal of Human-Computer Studies, Vol. 121 (2019), 58--72.
[19]
Zemin Liu, Wentao Zhang, Yuan Fang, Xinming Zhang, and Steven CH Hoi. 2020. Towards locality-aware meta-learning of tail node embeddings on networks. In Proceedings of CIKM . 975--984.
[20]
Yuanfu Lu, Yuan Fang, and Chuan Shi. 2020. Meta-learning on heterogeneous information networks for cold-start recommendation. In Proceedings of SIGKDD. 1563--1573.
[21]
Yuanfu Lu, Xiao Wang, Chuan Shi, Philip S Yu, and Yanfang Ye. 2019. Temporal network embedding with micro-and macro-dynamics. In Proceedings of CIKM . 469--478.
[22]
Franco Manessi, Alessandro Rozza, and Mario Manzo. 2020. Dynamic graph convolutional networks. Pattern Recognition, Vol. 97 (2020), 107000.
[23]
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In Proceedings of NeurIPS. 3111--3119.
[24]
Giang Hoang Nguyen, John Boaz Lee, Ryan A Rossi, Nesreen K Ahmed, Eunyee Koh, and Sungchul Kim. 2018. Continuous-time dynamic network embeddings. In Companion Proceedings of WWW . 969--976.
[25]
Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao Schardl, and Charles Leiserson. 2020. Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In Proceedings of AAAI, Vol. 34. 5363--5370.
[26]
Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael Bronstein. 2020. Temporal graph networks for deep learning on dynamic graphs. arXiv preprint arXiv:2006.10637 (2020).
[27]
Aravind Sankar, Yanhong Wu, Liang Gou, Wei Zhang, and Hao Yang. 2020. Dysat: Deep neural representation learning on dynamic graphs via self-attention networks. In Proceedings of WSDM. 519--527.
[28]
Georg Simmel. 1950. The sociology of georg simmel . Vol. 92892. Simon and Schuster.
[29]
Weiping Song, Zhiping Xiao, Yifan Wang, Laurent Charlin, Ming Zhang, and Jian Tang. 2019. Session-based social recommendation via dynamic graph attention networks. In Proceedings of WSDM. 555--563.
[30]
Peijie Sun, Le Wu, and Meng Wang. 2018. Attentive recurrent social recommendation. In Proceedings of SIGIR. 185--194.
[31]
Qiuling Suo, Jingyuan Chou, Weida Zhong, and Aidong Zhang. 2020. Tadanet: Task-adaptive network for graph-enriched meta-learning. In Proceedings of SIGKDD . 1789--1799.
[32]
Rakshit Trivedi, Mehrdad Farajtabar, Prasenjeet Biswal, and Hongyuan Zha. 2019. Dyrep: Learning representations over dynamic graphs. In Proceedings of ICLR .
[33]
Manasi Vartak, Arvind Thiagarajan, Conrado Miranda, Jeshua Bratman, and Hugo Larochelle. 2017. A meta-learning perspective on cold-start recommendations for items. In Proceedings of NeurIPS. 6907--6917.
[34]
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. arXiv preprint arXiv:1706.03762 (2017).
[35]
Petar Velivc ković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph attention networks. Proceedings of ICLR (2018).
[36]
Ricardo Vilalta and Youssef Drissi. 2002. A perspective view and survey of meta-learning. Artificial intelligence review, Vol. 18, 2 (2002), 77--95.
[37]
Yanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, and Pan Li. 2021. Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks. arXiv preprint arXiv:2101.05974 (2021).
[38]
Liang Xiang, Quan Yuan, Shiwan Zhao, Li Chen, Xiatian Zhang, Qing Yang, and Jimeng Sun. 2010. Temporal recommendation on graphs via long-and short-term preference fusion. In Proceedings of SIGKDD. 723--732.
[39]
Da Xu, Chuanwei Ruan, Evren Korpeoglu, Sushant Kumar, and Kannan Achan. 2020. Inductive representation learning on temporal graphs. Proceedings of ICLR (2020).
[40]
Huaxiu Yao, Chuxu Zhang, Ying Wei, Meng Jiang, Suhang Wang, Junzhou Huang, Nitesh Chawla, and Zhenhui Li. 2020. Graph few-shot learning via knowledge transfer. In Proceedings of AAAI, Vol. 34. 6656--6663.
[41]
Fan Zhou, Chengtai Cao, Kunpeng Zhang, Goce Trajcevski, Ting Zhong, and Ji Geng. 2019. Meta-gnn: On few-shot node classification in graph meta-learning. In Proceedings of CIKM . 2357--2360.
[42]
Lekui Zhou, Yang Yang, Xiang Ren, Fei Wu, and Yueting Zhuang. 2018. Dynamic network embedding by modeling triadic closure process. In Proceedings of AAAI, Vol. 32.
[43]
Yuan Zuo, Guannan Liu, Hao Lin, Jia Guo, Xiaoqian Hu, and Junjie Wu. 2018. Embedding temporal network via neighborhood formation. In Proceedings of SIGKDD . 2857--2866.

Cited By

View all
  • (2025)Prototypical networks with unlabeled data for few-shot node classificationEngineering Applications of Artificial Intelligence10.1016/j.engappai.2025.110088145(110088)Online publication date: Apr-2025
  • (2024)Dynamic Social Network Link Prediction Based on Bi-Layer Temporal ModelingModeling and Simulation10.12677/mos.2024.13323813:03(2611-2622)Online publication date: 2024
  • (2024)TGOnline: Enhancing Temporal Graph Learning with Adaptive Online Meta-LearningProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3626772.3657791(1659-1669)Online publication date: 10-Jul-2024
  • Show More Cited By

Index Terms

  1. Few-shot Link Prediction in Dynamic Networks

    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. dynamic network
    2. few-shot prediction
    3. graph neural networks
    4. link prediction
    5. meta-learning

    Qualifiers

    • Research-article

    Funding Sources

    • the National Natural Science Foundation of China

    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)153
    • Downloads (Last 6 weeks)14
    Reflects downloads up to 13 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2025)Prototypical networks with unlabeled data for few-shot node classificationEngineering Applications of Artificial Intelligence10.1016/j.engappai.2025.110088145(110088)Online publication date: Apr-2025
    • (2024)Dynamic Social Network Link Prediction Based on Bi-Layer Temporal ModelingModeling and Simulation10.12677/mos.2024.13323813:03(2611-2622)Online publication date: 2024
    • (2024)TGOnline: Enhancing Temporal Graph Learning with Adaptive Online Meta-LearningProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3626772.3657791(1659-1669)Online publication date: 10-Jul-2024
    • (2024)MetaHKG: Meta Hyperbolic Learning for Few-shot Temporal ReasoningProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval10.1145/3626772.3657711(59-69)Online publication date: 10-Jul-2024
    • (2024)Neural Kalman Filtering for Robust Temporal RecommendationProceedings of the 17th ACM International Conference on Web Search and Data Mining10.1145/3616855.3635837(836-845)Online publication date: 4-Mar-2024
    • (2024)A Simple but Effective Approach for Unsupervised Few-Shot Graph ClassificationProceedings of the ACM on Web Conference 202410.1145/3589334.3645587(4249-4259)Online publication date: 13-May-2024
    • (2024)Fuzzy Representation Learning on Dynamic GraphsIEEE Transactions on Systems, Man, and Cybernetics: Systems10.1109/TSMC.2023.332074954:2(878-890)Online publication date: Feb-2024
    • (2024)Dynamic Link Prediction for New Nodes in Temporal Graph Networks2024 International Joint Conference on Neural Networks (IJCNN)10.1109/IJCNN60899.2024.10650904(1-8)Online publication date: 30-Jun-2024
    • (2024)Dynamic Graph Contrastive Learning via Maximize Temporal ConsistencyPattern Recognition10.1016/j.patcog.2023.110144148:COnline publication date: 17-Apr-2024
    • (2024)ConTIG: Continuous representation learning on temporal interaction graphsNeural Networks10.1016/j.neunet.2024.106151172(106151)Online publication date: Apr-2024
    • Show More Cited By

    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