Abstract
The rapid development of heterogeneous networks has proposed new challenges to the long-standing link prediction problem. Existing models trained on the verified edge samples from different types usually learn type-specific knowledge, and their type-specific predictions may be contradictory for unverified edge samples with uncertain types. This challenge is termed edge-type disturbance in link prediction in heterogeneous networks. To address this challenge, we develop a disturbance-resilient prediction method (DRPM) comprising a structural characterizer, a type differentiator, and a resilient predictor. The structural characterizer is responsible for learning edge representations for link prediction. Concurrently, the type differentiator distinguishes type-specific edge representations to generate diverse type experts while maximizing their link prediction performances on specific types. Furthermore, the resilient predictor evaluates the reliability weights of different type experts to develop a resilient prediction mechanism to aggregate discriminable predictions. Extensive experiments conducted on various real-world datasets demonstrate the importance of the explainable introduction of the edge-type disturbance and the superiority of DRPM over state-of-the-art methods.
- [1] . 2021. Noise corrected sampling of online social networks. ACM Transactions on Knowledge Discovery from Data 15, 2 (2021), 1–21.Google ScholarDigital Library
- [2] . 2021. Identifying and evaluating anomalous structural change-based nodes in generalized dynamic social networks. ACM Transactions on the Web 15, 4 (2021), 1–22.Google ScholarDigital Library
- [3] . 2022. Multi-attribute based influence maximization in social networks: Algorithms and analysis. Theoretical Computer Science 921 (2022), 50–62.Google ScholarCross Ref
- [4] . 2022. Meta-path based neighbors for behavioral target generalization in sequential recommendation. IEEE Transactions on Network Science and Engineering 9, 3 (2022), 1658–1667.Google ScholarCross Ref
- [5] . 2021. Progresses and challenges in link prediction. iScience 24, 11 (2021), 103217.Google ScholarCross Ref
- [6] . 2021. Existence identifications of unobserved paths in graph-based social networks. World Wide Web 24 (2021), 157–173.Google ScholarCross Ref
- [7] . 2015. A novel page ranking algorithm based on triadic closure and hyperlink-induced topic search. Intelligent Data Analysis 19, 5 (2015), 1131–1149.Google ScholarCross Ref
- [8] . 2020. Time-invariant degree growth in preferential attachment network models. Physical Review E 101, 2 (2020).Google ScholarCross Ref
- [9] . 2011. Link prediction in complex networks: A survey. Physica A: Statistical Mechanics and Its Applications 390, 6 (2011), 1150–1170.Google ScholarCross Ref
- [10] . 2013. Deep learning approaches for link prediction in social network services. International Conference on Neural Information Processing. 425–432.Google ScholarDigital Library
- [11] . 2020. Predicting citation count of scientists as a link prediction problem. IEEE Transactions on Cybernetics 50, 10 (2020), 4518–4529.Google ScholarCross Ref
- [12] . 2021. Link prediction based on feature representation and fusion. Information Sciences 548, 16 (2021), 1–17.Google ScholarCross Ref
- [13] . 2019. Detecting and assessing anomalous evolutionary behaviors of nodes in evolving social networks. ACM Transactions on Knowledge Discovery from Data 13, 1 (2019), 1–24.Google ScholarDigital Library
- [14] . 2020. A nodes' evolution diversity inspired method to detect anomalies in dynamic social networks. IEEE Transactions on Knowledge and Data Engineering 32, 10 (2020), 1868–1880.Google ScholarCross Ref
- [15] . 2016. Social friend recommendation based on multiple network correlation. IEEE Transactions on Multimedia 18, 2 (2016), 287–299.Google ScholarDigital Library
- [16] . 2020. Discovering knowledge combinations in multidimensional collaboration network: A method based on trust link prediction and knowledge similarity. Knowledge-Based Systems 195, 2 (2020), 105701.Google ScholarCross Ref
- [17] . 2016. A survey of heterogeneous information network analysis. IEEE Transactions on Knowledge and Data Engineering 29, 1 (2016), 17–37.Google ScholarDigital Library
- [18] . 2011. Dynamics of bounded confidence opinion in heterogeneous social networks: Concord against partial antagonism. Physica A Statistical Mechanics and Its Applications 390, 16 (2011), 2945–2955.Google ScholarCross Ref
- [19] . 2016. Conflicts to harmony: A framework for resolving conflicts in heterogeneous data by truth discovery. IEEE Transactions on Knowledge and Data Engineering 28, 8 (2016), 1986–1999.Google ScholarDigital Library
- [20] . 2019. Towards confidence interval estimation in truth discovery. IEEE Transactions on Knowledge and Data Engineering 31, 3 (2019), 575–588.Google ScholarDigital Library
- [21] . 2014. Event detection over Twitter social media streams. The VLDB Journal 23, 3 (2014), 381–400.Google ScholarDigital Library
- [22] . 2017. Link prediction in multi-relational networks based on relational similarity. Information Sciences 394 (2017), 198–216.Google ScholarDigital Library
- [23] . 2015. Accuracy test for link prediction in terms of similarity index: The case of WS and BA models. Physica A: Statistical Mechanics and its Applications 429 (2015), 177–183.Google ScholarCross Ref
- [24] . 2014. A cluster based probabilistic model for link prediction to improve user interface over internet. International Journal of Computer Applications 106, 7 (2014), 18–22.Google Scholar
- [25] . 2017. Link sign prediction by variational bayesian probabilistic matrix factorization with student-t prior. Information Sciences 405 (2017), 175–189.Google ScholarCross Ref
- [26] . 2011. Evaluating network models: A likelihood Analysis. Europhysics Letters 98, 2 (2011), 28004–28009.Google ScholarCross Ref
- [27] . 2018. A generalized tree augmented naive bayes link prediction model. Journal of Computational Science 27 (2018), 206–217.Google ScholarCross Ref
- [28] . 2018. A survey on deep learning: algorithms, techniques, and applications. ACM Computing Surveys 51, 5 (2018), 1–36.Google ScholarDigital Library
- [29] . 2019. Relation structure-aware heterogeneous information network embedding. In Proceedings of the AAAI Conference on Artificial Intelligence. 4456–4463.Google ScholarDigital Library
- [30] . 2016. Link prediction in heterogeneous social networks. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. 609–617.Google ScholarDigital Library
- [31] . 2018. PME: Projected metric embedding on heterogeneous networks for link prediction. In Proceedings of the 24th ACM SIGKDD International Conference. 1177–1186.Google ScholarDigital Library
- [32] . 2020. Deep adversarial completion for sparse heterogeneous information network embedding. In Proceedings of the Web Conference. 508–518.Google ScholarDigital Library
- [33] . 2018. Link prediction based on graph neural networks. In Proceedings of the 32nd International Conference on Neural Information Processing Systems. 5171–5181.Google ScholarDigital Library
- [34] . 2021. Self-supervised learning of contextual embeddings for link prediction in heterogeneous networks. In Proceedings of the Web Conference. 2946–2957.Google ScholarDigital Library
- [35] . 2019. Representation learning for attributed multiplex heterogeneous network. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1358–1368.Google ScholarDigital Library
- [36] . 2019. Adversarial learning on heterogeneous information networks. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 120–129.Google ScholarDigital Library
- [37] . 2020. Disenhan: Disentangled heterogeneous graph attention network for recommendation. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 1605–1614.Google ScholarDigital Library
- [38] . 2021. Social recommendation with self-supervised metagraph informax network. In Proceedings of the 30th ACM International Conference on Information and Knowledge Management. 1160–1169.Google ScholarDigital Library
- [39] . 2019. Metapath guided heterogeneous graph neural network for intent recommendation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2478–2486.Google ScholarDigital Library
- [40] . 2021. Heterogeneous graph propagation network. IEEE Transactions on Knowledge and Data Engineering (2021). 1–1.Google ScholarCross Ref
- [41] . 2021. Heterogeneous graph structure learning for graph neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence. 4697–4705.Google ScholarCross Ref
- [42] . 2020. MARU: Meta-context aware random walks for heterogeneous network representation learning. In Proceedings of the 29th ACM International Conference on Information and Knowledge Management. 575–584.Google ScholarDigital Library
- [43] . 2017. metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD International Conference. 135–144.Google ScholarDigital Library
- [44] . 2022. Adversarial caching training: Unsupervised inductive network representation learning on large-scale graphs. IEEE Transactions on Neural Networks and Learning Systems 33, 12 (2022), 7079–7090.Google ScholarCross Ref
- [45] . 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the International Conference on Learning Representation.Google Scholar
- [46] . 2016. Node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 855–864.Google ScholarDigital Library
- [47] . 2023. Multitype perception method for drug-target interaction prediction. IEEE/ACM Transactions on Computational Biology and Bioinformatics (2023). 1–10.Google Scholar
- [48] , 2014. Resolving Conflicts in heterogeneous data by truth discovery and source reliability estimation. In Proceedings of the ACM SIGMOD International Conference on Management of Data. 1187–1198.Google ScholarDigital Library
- [49] . 2021. Multi-scale attributed node embedding. Journal of Complex Networks 9, 2 (2021).Google ScholarCross Ref
- [50] . 2019. Representation learning for heterogeneous information networks via embedding events. In Proceedings of the 26th International Conference on Neural Information Processing. 327–339.Google ScholarDigital Library
- [51] . 1999. Least squares support vector machine classifiers. Neural Processing Letters 9, 3 (1999), 293–300.Google ScholarDigital Library
- [52] . 2013. Applied Logistic Regression. John Wiley and Sons.Google ScholarCross Ref
- [53] . 2014. Recommending research collaborations using link prediction and random forest classifiers. Scientometrics 101, 2 (2014), 1461–1473.Google ScholarDigital Library
Index Terms
- Resisting the Edge-Type Disturbance for Link Prediction in Heterogeneous Networks
Recommendations
Link Prediction in Heterogeneous Social Networks
CIKM '16: Proceedings of the 25th ACM International on Conference on Information and Knowledge ManagementA heterogeneous social network is characterized by multiple link types which makes the task of link prediction in such networks more involved. In the last few years collective link prediction methods have been proposed for the problem of link prediction ...
Meta-learning adaptation network for few-shot link prediction in heterogeneous social networks
AbstractLink prediction, which aims to predict future or missing links among nodes, is a crucial research problem in social network analysis. A unique few-shot challenge is link prediction on newly emerged link types without sufficient verification ...
Link prediction measures in various types of information networks: a review
ASONAM '18: Proceedings of the 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and MiningAn information network is represented as a graph where nodes represent entities and edges represent interactions between nodes. There can be multiple types of nodes and edges in such networks giving rise to homogeneous, multi-relational and ...
Comments