To bring the full benefits of machine learning to defense modeling and simulation, it is essential to first learn useful representations for sparse graphs consisting of both key entities (vertices) and their relationships (edges). Here, we present a new model, the Joint Sparsity-Biased Variational Graph AutoEncoder (JSBVGAE), capable of learning embedded representations of nodes from which both sparse network topologies and node features can be jointly and accurately reconstructed. We show that our model outperforms the previous state of the art on standard link-prediction and node-classification tasks, and achieves significantly higher whole-network reconstruction accuracy, while reducing the number of trained parameters.
ParnoBPerrigAGligorV. Distributed detection of node replication attacks in sensor networks. In: 2005 IEEE Symposium on Security and Privacy (S&P’05), 2005. Piscataway, NJ: IEEE, pp. 49–63.
2.
YangZZhangYDaiY. Defending against social network sybils with interaction graph embedding. In: 2018 IEEE Conference on Communications and Network Security (CNS), 2018. Piscataway, NJ: IEEE, pp. 1–9.
3.
KottASwamiAWestBJ. The internet of battle things. Computer2016; 49(12): 70–75.
4.
KipfTNWellingM. Variational graph auto-encoders. In: NeurIPS Workshop on Bayesian Deep Learning, 2016.
5.
TranPV. Learning to make predictions on graphs with autoencoders. In: 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA), 2018. Piscataway, NJ: IEEE, pp. 237–245.
6.
XieYJinPGongM, et al. Multi-task network representation learning. Front Neurosci2020; 14.
7.
LeriqueSAbitbolJLKarsaiM. Joint embedding of structure and features via graph convolutional networks. Appl Netw Sci2020; 5(1): 1–24.
8.
KipfTNWellingM. Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, 2017.
9.
SenPNamataGBilgicM, et al. Collective classification in network data. AI Magazine2008; 29(3): 93–93.
10.
GetoorL. Link-based classification. In:BandyopadhyayS, et al. (eds) Advanced methods for knowledge discovery from complex data. London: Springer, 2005. pp. 189–207.
11.
NamataGLondonBGetoorL, et al. Query-driven active surveying for collective classification. In: 10th International Workshop on Mining and Learning with Graphs, volume 8, 2012.
12.
TianYNiuYYanJ, et al. Inferring private attributes based on graph convolutional neural network in social networks. In: 2019 International Conference on Networking and Network Applications (NaNA), 2019. Piscataway, NJ: IEEE, pp. 186–190.
13.
DingXLiuTDuanJ, et al. Mining user consumption intention from social media using domain adaptive convolutional neural network. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, volume 15, 2015. pp. 2389–2395.
14.
MedranoJLinFJ. Enabling machine learning across heterogeneous sensor networks with graph autoencoders. In: European Conference on Ambient Intelligence, 2019. Berlin: Springer, pp. 153–169.
15.
CartwrightMCramerJSalamonJ, et al. Tricycle: audio representation learning from sensor network data using self-supervision. In: 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2019. Piscataway, NJ: IEEE, pp. 278–282.
16.
WangMYuLZhengD, et al. Deep graph library: Towards efficient and scalable deep learning on graphs. arXiv preprint2019; (arXiv:1909.01315).
17.
YangZCohenWSalakhudinovR. Revisiting semi-supervised learning with graph embeddings. In: International conference on machine learning, 2016. PMLR, pp. 40–48.
18.
LuQGetoorL. Link-based classification. In: Proceedings of the Twentieth International Conference on International Conference on Machine Learning, 2003. ICML’03, AAAI Press., pp. 496–503.
19.
PerozziBAl-RfouRSkienaS. Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014. KDD ’14, New York, NY, USA: Association for Computing Machinery. pp. 701–710.
20.
JacomyMVenturiniTHeymannS, et al. Forceatlas2, a continuous graph layout algorithm for handy network visualization designed for the gephi software. PloS one2014; 9(6): e98679.
21.
McInnesLHealyJSaulN, et al. Umap: uniform manifold approximation and projection. J Open Source Softw2018; 3(29): 861.
22.
XuZKeY. Effective and efficient spectral clustering on text and link data. In: Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, 2016. CIKM ’16, New York, NY, USA: Association for Computing Machinery. pp. 357–366.
23.
ChunaevP. Community detection in node-attributed social networks: a survey. Comput Sci Rev2020; 37: 100286.
24.
HamiltonWL. Graph representation learning. Synthesis Lectures on Artifical Intelligence and Machine Learning2020; 14(3): 1–159.
25.
BennettBT. Understanding, assessing, and responding to terrorism: protecting critical infrastructure and personnel. New York: John Wiley & Sons, 2018.
