ABSTRACT
We study a novel problem of continuously predicting a number of user-subscribed continuous analytics targets (CATs) in dynamic networks. Our architecture includes any dynamic graph neural network model as the back end applied over the network data, and per CAT front end models that return results with their confidence to users. We devise a data filtering algorithm that feeds a provably optimal subset of data in the embedding space from back end model to front end models. Secondly, to ensure fairness in terms of query result accuracy for different CATs and users, we propose a fairness metric and a fairness-aware training scheduling algorithm, along with accuracy guarantees on fairness estimation. Our experiments over five real-world datasets show that our proposed solution is effective, efficient, fair, extensible, and adaptive.
Supplemental Material
- J. Ahmed and M. Ahmed. 2018. Semantic web approach of integrating big data -- A review. International Journal of Computer Sciences and Engineering (2018).Google Scholar
- N. Alon and J. Spencer. 1992. The Probabilistic Method. New York: Wiley.Google ScholarDigital Library
- Brian Babcock, Shivnath Babu, Mayur Datar, Rajeev Motwani, and Jennifer Widom. 2002. Models and Issues in Data Stream Systems. In Proceedings of the Twenty-First ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems (PODS '02). 1--16.Google ScholarDigital Library
- Shivnath Babu and Jennifer Widom. 2001. Continuous queries over data streams. ACM SIGMOD Record, Vol. 30, 3 (2001), 109--120.Google ScholarDigital Library
- Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. 2013. Translating Embeddings for Modeling Multi-relational Data. In Advances in Neural Information Processing Systems 26. Curran Associates, Inc.Google Scholar
- Elizabeth Boschee, Jennifer Lautenschlager, Sean O'Brien, Steve Shellman, James Starz, and Michael Ward. 2015. ICEWS coded event data. Harvard Dataverse, Vol. 12 (2015).Google Scholar
- Michael M. Bronstein, Joan Bruna, Taco Cohen, and Petar Veličković. 2021. Geometric Deep Learning: Grids, Groups, Graphs Geodesics and Gauges. arXiv:2104.13478 (2021).Google Scholar
- N Cesa-Bianchi and G Lugosi. 2006. Prediction, learning, and games. Cambridge University Press.Google Scholar
- K Crammer, O Dekel, J Keshet, S Shalev-Shwartz, and Y Singer. 2006. Online passive-aggressive algorithms. JMLR (2006).Google Scholar
- Michael Crawshaw. 2020. Multi-Task Learning with Deep Neural Networks: A Survey. arXiv preprint arXiv:2009.09796 (2020).Google Scholar
- Devdatt P. Dubhashi and Alessandro Panconesi. 2009. Concentration of Measure for the Analysis of Randomized Algorithms. Cambridge University Press.Google Scholar
- Cynthia Dwork, Moritz Hardty, Toniann Pitassiz, Omer Reingold, and Richard Zemel. 2012. Fairness Through Awareness. In The 3rd Innovations in Theoretical Computer Science.Google Scholar
- R. S. Evans. 2016. Electronic Health Records: Then, Now, and in the Future. IMIA Yearbook of Medical Informatics, Vol. Suppl 1 (2016).Google Scholar
- Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q. Weinberger. 2017. On Calibration of Modern Neural Networks. In Proceedings of the 34th International Conference on Machine Learning (ICML 2017).Google Scholar
- S.C.H. Hoi, J Wang, and P Zhao. 2014. Libol: A library for online learning algorithms. Journal of Machine (2014).Google Scholar
- S. C. H. Hoi, D. Sahoo, J. Lu, and P. Zhao. 2018. Online learning: A comprehensive survey. arXiv preprint arXiv:1802.02871 (2018).Google Scholar
- Woojeong Jin, Meng Qu, Xisen Jin, and Xiang Ren. 2020. Recurrent Event Network: Autoregressive Structure Inference over Temporal Knowledge Graphs. In EMNLP.Google Scholar
- AEW Johnson, TJ Pollard, L Shen, L Lehman, M Feng, M Ghassemi, B Moody, P Szolovits, LA Celi, and RG Mark. 2016. MIMIC-III, a freely accessible critical care database. Scientific Data (2016).Google Scholar
- Justin M. Johnson and Taghi M. Khoshgoftaar. 2019. Survey on deep learning with class imbalance. Journal of Big Data, Vol. 6, 27 (2019).Google ScholarCross Ref
- M. Seyed Kazemi. 2022. Dynamic Graph Neural Networks. In Graph Neural Networks: Foundations, Frontiers, and Applications, Lingfei Wu, Peng Cui, Jian Pei, and Liang Zhao (Eds.). Springer Singapore, Singapore, 323--349.Google Scholar
- Thomas N Kipf and Max Welling. 2016. Semi-supervised classification with graph convolutional networks. IEEE Transactions on Neural Networks, Vol. 5, 1 (2016), 61--80.Google Scholar
- Julien Leblay and Melisachew Wudage Chekol. 2018. Deriving validity time in knowledge graph. In The Web Conference.Google ScholarDigital Library
- J Lee, J Yun, S Hwang, and E Yang. 2017. Lifelong learning with dynamically expandable networks. arXiv:1708.01547 (2017).Google Scholar
- Kalev Leetaru and Philip A Schrodt. 2013. GDELT: Global data on events, location, and tone, 1979--2012. ISA annual convention, Vol. 2 (2013), 1--49.Google Scholar
- Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollar. 2017. Focal Loss for Dense Object Detection. In ICCV.Google Scholar
- Xuanming Liu and Tingjian Ge. 2020. Mining Dynamic Graph Streams for Predictive Queries Under Resource Constraints. In PAKDD.Google Scholar
- Andrew McGregor. 2014. Graph stream algorithms: A survey. ACM SIGMOD Record, Vol. 43, 1 (2014), 9--20.Google ScholarDigital Library
- Ninareh Mehrabi, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. 2022. A Survey on Bias and Fairness in Machine Learning. Comput. Surveys, Vol. 54, 6 (2022), 1--35.Google ScholarDigital Library
- S.P. Meyn and R.L. Tweedie. 2012. Markov Chains and Stochastic Stability. Springer London.Google Scholar
- M. Mitzenmacher and E.Upfal. 2005. Probability and Computing: Randomized Algorithms and Probabilistic Analysis. Cambridge University Press.Google ScholarDigital Library
- Jooyoung Moon, Jihyo Kim, Younghak Shin, and Sangheum Hwang. 2020. Confidence-Aware Learning for Deep Neural Networks. In ICML.Google Scholar
- Faisal Mushtaq and Matt E. Moore. 2020. Cloud-based interoperability will accelerate clinical outcomes. Physicians Practice (2020).Google Scholar
- Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B. Schardl, and Charles E. Leiserson. 2020. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs. In AAAI.Google Scholar
- German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, and Stefan Wermter. 2019. Continual lifelong learning with neural networks: A review. Neural Networks, Vol. 113 (2019), 54--71.Google ScholarDigital Library
- Frank Rosenblatt. 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, Vol. 65, 6 (1958).Google Scholar
- Tara Safavi, Danai Koutra, and Edgar Meij. 2020. Evaluating the Calibration of Knowledge Graph Embeddings for Trustworthy Link Prediction. In The 2020 Conference on Empirical Methods in Natural Language Processing.Google Scholar
- D Sahoo, S. C. H. Hoi, and P Zhao. 2016. Cost sensitive online multiple kernel classification. ACML (2016).Google Scholar
- Doyen Sahoo, Quang Pham, Jing Lu, and Steven C. H. Hoi. 2018. Online Deep Learning: Learning Deep Neural Networks on the Fly. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18. International Joint Conferences on Artificial Intelligence Organization, 2660--2666.Google Scholar
- J. Skarding, B. Gabrys, and K. Musial. 2021. Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey. IEEE Acces, Vol. 9 (2021).Google Scholar
- Naisha Sultana1, Gandikota Ramu, and B. Eswara Reddy. 2014. Cloud-based Development of Smart and Connected Data in Healthcare Application. International Journal of Distributed and Parallel Systems, Vol. 5, 6 (2014).Google Scholar
- Pedro Tabacof and Luca Costabello. 2020. Probability Calibration for Knowledge Graph Embedding Models. In The International Conference on Learning Representations (ICLR).Google Scholar
- V. A. Traag, L. Waltman, and N. J. van Eck. 2019. From Louvain to Leiden: guaranteeing well-connected communities. Scientific Reports, Vol. 9, 5233 (2019).Google Scholar
- Rakshit Trivedi, Hanjun Dai, Yichen Wang, and Le Song. 2017. Know-evolve: Deep temporal reasoning for dynamic knowledge graphs. In ICML.Google ScholarDigital Library
- Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2018. Graph Attention Networks. ICLR (2018).Google Scholar
- Junshan Wang, Guojie Song, Yi Wu, and Liang Wang. 2020. Streaming Graph Neural Networks via Continual Learning. In CIKM.Google Scholar
- Rex Ying, Zhaoyu Lou, Jiaxuan You, Chengtao Wen, Arquimedes Canedo, and Jure Leskovec. 2020. Neural Subgraph Matching. In CoRR abs/2007.03092.Google Scholar
- Ling Zhao, Yujiao Song, Chao Zhang, Yu Liu, Pu Wang, Tao Lin, Min Deng, and Haifeng Li. 2020. T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction. IEEE Transactions on Intelligent Transportation Systems, Vol. 21, 9 (2020), 3848--3858.Google ScholarCross Ref
- Peixiang Zhao, Charu Aggarwal, and Gewen He. 2016. Link Prediction in Graph Streams. In ICDE.Google Scholar
- G Zhou, K Sohn, and H Lee. 2012. Online incremental feature learning with denoising autoencoders. AISTATS (2012).Google Scholar
- M Zinkevich. 2003. Online convex programming and generalized infinitesimal gradient ascent. In ICML.Google Scholar
Index Terms
- Fairness-Aware Continuous Predictions of Multiple Analytics Targets in Dynamic Networks
Recommendations
Airtime Fairness for IEEE 802.11 Multirate Networks
Under a multi rate network scenario, the IEEE 802.11 DCF MAC fails to provide air-time fairness for all competing stations since the protocol is designed for ensuring max-min throughput fairness and the maximum achievable throughput by any station gets ...
Fairness in multi-hop wireless backhaul networks: a dynamic estimation approach
QShine '08: Proceedings of the 5th International ICST Conference on Heterogeneous Networking for Quality, Reliability, Security and RobustnessIn this work, we consider the problem of fairness for Transit Access Points (TAP) in multi-hop wireless backhaul networks. Existing approaches are not practical due to the requirement for modifications to the MAC layer or queueing operations of TAPs, or ...
Dynamic Contention Window Control Mechanism to Achieve Fairness between Uplink and Downlink Flows in IEEE 802.11 Wireless LANs
This paper considers a fairness issue between uplink and downlink flows in IEEE 802.11 wireless LANs, where uplink flows dominate over downlink flows in terms of wireless bandwidth usage. As a solution to this unfairness, we propose modifying the IEEE ...
Comments