ABSTRACT
Clustering is an important unsupervised learning method with serious challenges when data is sparse and high-dimensional. Generated clusters are often evaluated with general measures, which may not be meaningful or useful for practical applications and domains. Using a distance metric, a clustering algorithm searches through the data space, groups close items into one cluster, and assigns far away samples to different clusters. In many real-world applications, the number of dimensions is high and data space becomes very sparse. Selection of a suitable distance metric is very difficult and becomes even harder when categorical data is involved. Moreover, existing distance metrics are mostly generic, and clusters created based on them will not necessarily make sense to domain-specific applications. One option to address these challenges is to integrate domain-defined rules and guidelines into the clustering process. In this work we propose a GAN-based approach called Catalysis Clustering to incorporate domain knowledge into the clustering process. With GANs we generate catalysts, which are special synthetic points drawn from the original data distribution and verified to improve clustering quality when measured by a domain-specific metric. We then perform clustering analysis using both catalysts and real data. Final clusters are produced after catalyst points are removed. Experiments on two challenging real-world datasets clearly show that our approach is effective and can generate clusters that are meaningful and useful for real-world applications.
- L. N. Allen and L. C. Rose. 2006. Financial Survival Analysis of Defaulted Debtors. The Journal of the Operational Research Society, Vol. 57, 6 (2006), 630 -- 636.Google ScholarCross Ref
- Martin Arjovsky, Soumith Chintala, and Léon Bottou. 2017. Wasserstein gan. arXiv preprint arXiv:1701.07875 (2017).Google Scholar
- Yale Chang, Junxiang Chen, Michael H Cho, Peter J Castaidi, Edwin K Silverman, and Jennifer G Dy. 2017. Clustering with domain-specific usefulness scores. In Proceedings of the 2017 SIAM International Conference on Data Mining. SIAM, 207--215.Google ScholarCross Ref
- Nitesh V Chawla, Kevin W Bowyer, Lawrence O Hall, and W Philip Kegelmeyer. 2002. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, Vol. 16 (2002), 321--357.Google ScholarCross Ref
- Xi Chen, Yan Duan, Rein Houthooft, John Schulman, Ilya Sutskever, and Pieter Abbeel. 2016. Infogan: Interpretable representation learning by information maximizing generative adversarial nets. In Advances in neural information processing systems. 2172--2180.Google ScholarDigital Library
- The International Cancer Genome Consortium. 2010. International network of cancer genome projects. Nature, Vol. 464 (15 04 2010), 993 -- 998. http://dx.doi.org/10.1038/nature08987Google Scholar
- Pietro Coretto, Angela Serra, Roberto Tagliaferri, and Jonathan Wren. 2018. Robust clustering of noisy high-dimensional gene expression data for patients subtyping. Bioinformatics (2018).Google Scholar
- Kamran Ghasedi, Xiaoqian Wang, Cheng Deng, and Heng Huang. 2019. Balanced self-paced learning for generative adversarial clustering network. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4391--4400.Google ScholarCross Ref
- Manish Kumar Goel, Pardeep Khanna, and Jugal Kishore. 2010. Understanding survival analysis: Kaplan-Meier estimate. International journal of Ayurveda research, Vol. 1, 4 (2010), 274.Google Scholar
- Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Advances in neural information processing systems. 2672--2680.Google Scholar
- Pranab Haldar, Ian D Pavord, Dominic E Shaw, Michael A Berry, Michael Thomas, Christopher E Brightling, Andrew J Wardlaw, and Ruth H Green. 2008. Cluster analysis and clinical asthma phenotypes. American journal of respiratory and critical care medicine, Vol. 178, 3 (2008), 218--224.Google Scholar
- Hui Han, Wen-Yuan Wang, and Bing-Huan Mao. 2005. Borderline-SMOTE: a new over-sampling method in imbalanced data sets learning. In International Conference on Intelligent Computing. Springer, 878--887.Google ScholarDigital Library
- J. A. Hartigan and M. A. Wong. 1979. Algorithm AS 136: A K-Means Clustering Algorithm. Journal of the Royal Statistical Society. Series C (Applied Statistics), Vol. 28, 1 (1979), 100--108. https://doi.org/10.2307/2346830Google ScholarCross Ref
- Haibo He, Yang Bai, Edwardo A Garcia, and Shutao Li. 2008. ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In Neural Networks, 2008. IJCNN 2008.(IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on. IEEE, 1322--1328.Google Scholar
- Haibo He and Edwardo A Garcia. 2009. Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, Vol. 21, 9 (2009), 1263--1284.Google ScholarDigital Library
- Matan Hofree, John P Shen, Hannah Carter, Andrew Gross, and Trey Ideker. 2013. Network-based stratification of tumor mutations. Nature Methods, Vol. 10 (15 09 2013), 1108 -- 1115. http://dx.doi.org/10.1038/nmeth.2651Google ScholarCross Ref
- Christian O Jacke, Iris Reinhard, and Ute S Albert. 2013. Using relative survival measures for cross-sectional and longitudinal benchmarks of countries, states, and districts: the BenchRelSurv-and BenchRelSurvPlot-macros. BMC public health, Vol. 13, 1 (2013), 34.Google Scholar
- Michael S Lawrence, Petar Stojanov, Craig H Mermel, James T Robinson, Levi A Garraway, Todd R Golub, Matthew Meyerson, Stacey B Gabriel, Eric S Lander, and Gad Getz. 2014. Discovery and saturation analysis of cancer genes across 21 tumour types. Nature, Vol. 505, 7484 (2014), 495.Google Scholar
- Michael S Lawrence, Petar Stojanov, Paz Polak, Gregory V Kryukov, Kristian Cibulskis, Andrey Sivachenko, Scott L Carter, Chip Stewart, Craig H Mermel, Steven A Roberts, et al. 2013. Mutational heterogeneity in cancer and the search for new cancer-associated genes. Nature, Vol. 499, 7457 (2013), 214.Google Scholar
- Daniel D Lee and H Sebastian Seung. 1999. Learning the parts of objects by non-negative matrix factorization. Nature, Vol. 401, 6755 (1999), 788--791.Google Scholar
- Fang Liu, Licheng Jiao, and Xu Tang. 2019. Task-oriented GAN for PolSAR image classification and clustering. IEEE transactions on neural networks and learning systems, Vol. 30, 9 (2019), 2707--2719.Google ScholarCross Ref
- Stefano Monti, Pablo Tamayo, Jill Mesirov, and Todd Golub. 2003. Consensus clustering: a resampling-based method for class discovery and visualization of gene expression microarray data. Machine learning, Vol. 52, 1--2 (2003), 91--118.Google Scholar
- Sudipto Mukherjee, Himanshu Asnani, Eugene Lin, and Sreeram Kannan. 2019. Clustergan: Latent space clustering in generative adversarial networks. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33. 4610--4617.Google ScholarDigital Library
- The Cancer Genome Atlas Research Network. 2011. Integrated genomic analyses of ovarian carcinoma. Nature, Vol. 474 (29 06 2011), 609 -- 615. http://dx.doi.org/10.1038/nature10166Google Scholar
- The Cancer Genome Atlas Research Network. 2013. Integrated genomic characterization of endometrial carcinoma. Nature, Vol. 497 (01 05 2013), 67 -- 73. http://dx.doi.org/10.1038/nature12113Google Scholar
- José Pereira. 2014. Survival Analysis Employed in Predicting Corporate Failure: A Forecasting Model Proposal., Vol. 7 (04 2014).Google Scholar
- Catherine R Planey and Olivier Gevaert. 2016. CoINcIDE: A framework for discovery of patient subtypes across multiple datasets. Genome medicine, Vol. 8, 1 (2016), 27.Google Scholar
- Jost Tobias Springenberg. 2015. Unsupervised and semi-supervised learning with categorical generative adversarial networks. arXiv preprint arXiv:1511.06390 (2015).Google Scholar
- Michael Steinbach, Levent Ertöz, and Vipin Kumar. 2004. The challenges of clustering high dimensional data. In New directions in statistical physics. Springer, 273--309.Google Scholar
- Mark Stevenson and IVABS EpiCentre. 2009. An introduction to survival analysis. EpiCentre, IVABS, Massey University (2009).Google Scholar
- Mike Stoolmiller and James Snyder. 2013. Embedding multilevel survival analysis of dyadic social interaction in structural equation models: hazard rates as both outcomes and predictors. Journal of pediatric psychology, Vol. 39, 2 (2013), 222--232.Google ScholarCross Ref
- Kelly C Vranas, Jeffrey K Jopling, Timothy E Sweeney, Meghan C Ramsey, Arnold S Milstein, Christopher G Slatore, Gabriel J Escobar, and Vincent X Liu. 2017. Identifying Distinct Subgroups of Intensive Care Unit Patients: a Machine Learning Approach. Critical care medicine, Vol. 45, 10 (2017), 1607.Google Scholar
Index Terms
- Catalysis Clustering with GAN by Incorporating Domain Knowledge
Recommendations
The impact of random models on clustering similarity
Clustering is a central approach for unsupervised learning. After clustering is applied, the most fundamental analysis is to quantitatively compare clusterings. Such comparisons are crucial for the evaluation of clustering methods as well as other tasks ...
Modified CURE algorithm with enhancement to identify number of clusters
In this paper, we present an effective way of identifying number of clusters k based on density of data in given dataset and optimality of clusters formed. We have used internal evaluation of clustering to choose optimal set of clusters after narrowing ...
Atomic-layer-deposited Al2O3 and HfO2 on GaN: A comparative study on interfaces and electrical characteristics
Al"2O"3, HfO"2, and composite HfO"2/Al"2O"3 films were deposited on n-type GaN using atomic layer deposition (ALD). The interfacial layer of GaON and HfON was observed between HfO"2 and GaN, whereas the absence of an interfacial layer at Al"2O"3/GaN was ...
Comments