{"type":"ScholarlyArticle","title":"BlockEcho: Retaining Long-Range Dependencies for Imputing Block-Wise Missing Data","authors":[{"name":"Qiao Han","slug":"qiao-han","given":"Qiao","family":"Han","affiliation":"Nanyang Technological University"},{"name":"Mingqian Li","slug":"mingqian-li","given":"Mingqian","family":"Li","affiliation":"Nanyang Technological University"},{"name":"Yao Yang","slug":"yao-yang","given":"Yao","family":"Yang","affiliation":"Nanyang Technological University"},{"name":"Yiteng Zhai","slug":"yiteng-zhai","given":"Yiteng","family":"Zhai","affiliation":"Nanyang Technological University"}],"abstract":"Block-wise missing data poses significant challenges in real-world data imputation tasks. Compared to scattered missing data, block-wise gaps exacerbate adverse effects on subsequent analytic and machine learning tasks, as the lack of local neighboring elements significantly reduces the interpolation capability and predictive power. However, this issue has not received adequate attention. Most SOTA matrix completion methods appeared less effective, primarily due to overreliance on neighboring elements for predictions. We systematically analyze the issue and propose a novel matrix completion method \"BlockEcho\" for a more comprehensive solution. This method creatively integrates Matrix Factorization (MF) within Generative Adversarial Networks (GAN) to explicitly retain long-distance inter-element relationships in the original matrix. Besides, we incorporate an additional discriminator for GAN, comparing the generator's intermediate progress with pre-trained MF results to constrain high-order feature distributions. Subsequently, we evaluate BlockEcho on public datasets across three domains. Results demonstrate superior performance over both traditional and SOTA methods when imputing block-wise missing data, especially at higher missing rates. The advantage also holds for scattered missing data at high missing rates. We also contribute on the analyses in providing theoretical justification on the optimality and convergence of fusing MF and GAN for missing block data.","doi":"10.24963/ijcai.2024/453","url":"https://ijcai.org/proceedings/2024/453","pdf":"https://ijcai.org/proceedings/2024/0453.pdf","markdown":"https://ijcai.org/proceedings/2024/453.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/453","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":453,"pages":{"first":4098,"last":4106},"keywords":["Machine Learning: ML: Generative models","Data Mining: DM: Other"],"videos":[],"references":[{"position":1,"raw":"[Buuren and Oudshoorn, 2000] S. Van Buuren and C. G. M Oudshoorn. Multivariate imputation by chained equations : Mice v1.0 user's manual. 2000.","title":"Multivariate imputation by chained equations : Mice v1.0 user's manual","authors":"S Van Buuren, C G Oudshoorn","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Chang et al., 2023] Zhuoqing Chang, Shubo Liu, Zhaohui Cai, and Guoqing Tu. Anode-gan: Incomplete time se- ries imputation by augmented neural ode-based generative adversarial networks. In International Conference on Ar- tificial Neural Networks, pages 16-27. Springer, 2023.","title":"Anode-gan: Incomplete time series imputation by augmented neural ode-based generative adversarial networks","authors":"Chang","year":"2023","venue":"International Conference on Artificial Neural Networks","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Gao et al., 2020] Xin Gao, Fang Deng, and Xianghu Yue. Data augmentation in fault diagnosis based on the wasser- stein generative adversarial network with gradient penalty. Neurocomputing, 396:487-494, 2020.","title":"Data augmentation in fault diagnosis based on the wasserstein generative adversarial network with gradient penalty","authors":"Xin Gao, Fang Deng, Xianghu Yue","year":"2020","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Gold and Bentler, 2000] Michael Steven Gold and Peter M Bentler. Treatments of missing data: A monte carlo com- parison of rbhdi, iterative stochastic regression imputation, and expectation-maximization. Structural Equation Mod- eling, 7(3):319-355, 2000.","title":"Treatments of missing data: A monte carlo comparison of rbhdi, iterative stochastic regression imputation, and expectation-maximization","authors":"Bentler ; Gold, Steven Michael, Peter M Gold, Bentler","year":"2000","venue":"Structural Equation Modeling","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Goodfellow et al., 2020] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial networks. Communications of the ACM, 63(11):139-144, 2020.","title":"Generative adversarial networks","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2020","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Harper and Konstan, 2015] F Maxwell Harper and Joseph A Konstan. The movielens datasets: History and context. Acm transactions on interactive intelligent systems (tiis), 5(4):1-19, 2015.","title":"The movielens datasets: History and context. Acm transactions on interactive intelligent systems","authors":"Maxwell Harper, Joseph A Konstan","year":"2015","venue":"tiis)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hastie et al., 2015] Trevor Hastie, Rahul Mazumder, Ja- son D Lee, and Reza Zadeh. Matrix completion and low- rank svd via fast alternating least squares. The Journal of Machine Learning Research, 16(1):3367-3402, 2015.","title":"Matrix completion and lowrank svd via fast alternating least squares","authors":"Trevor Hastie, Rahul Mazumder, Jason D Lee, Reza Zadeh","year":"2015","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kong et al., 2023] Xiangjie Kong, Wenfeng Zhou, Guo- jiang Shen, Wenyi Zhang, Nali Liu, and Yao Yang. Dy- namic graph convolutional recurrent imputation network for spatiotemporal traffic missing data. Knowledge-Based Systems, 261:110188, 2023.","title":"Dynamic graph convolutional recurrent imputation network for spatiotemporal traffic missing data","authors":"Kong","year":"2023","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lee and Seung, 2000] Daniel Lee and H Sebastian Seung. Algorithms for non-negative matrix factorization. Ad- vances in neural information processing systems, 13, 2000.","title":"Algorithms for non-negative matrix factorization","authors":"Daniel Lee, H Sebastian, Seung","year":"2000","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lee et al., 2019] Dongwook Lee, Junyoung Kim, Won-Jin Moon, and Jong Chul Ye. Collagan: Collaborative gan for missing image data imputation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2487-2496, 2019.","title":"Collagan: Collaborative gan for missing image data imputation","authors":"Dongwook Lee, Junyoung Kim, Won-Jin Moon, Jong Chul, Ye","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Li et al., 2017] Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. Diffusion convolutional recurrent neural net- work: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926, 2017.","title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","authors":"Yaguang Li, Rose Yu, Cyrus Shahabi, Yan Liu","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2019] Steven Cheng-Xian Li, Bo Jiang, and Ben- jamin Marlin. Misgan: Learning from incomplete data with generative adversarial networks. arXiv preprint arXiv:1902.09599, 2019.","title":"Misgan: Learning from incomplete data with generative adversarial networks","authors":"Steven Cheng-Xian, Bo Li, Benjamin Jiang, Marlin","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mescheder et al., 2017] Lars Mescheder, Sebastian Nowozin, and Andreas Geiger. The numerics of gans. Advances in neural information processing systems, 30, 2017.","title":"The numerics of gans","authors":"Mescheder","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Miyato et al., 2018] Takeru Miyato, Toshiki Kataoka, Masanori Koyama, and Yuichi Yoshida. Spectral normal- ization for generative adversarial networks. arXiv preprint arXiv:1802.05957, 2018.","title":"Spectral normalization for generative adversarial networks","authors":"Miyato","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Neves et al., 2021] Diogo Telmo Neves, Marcel Ganesh Naik, and Alberto Proenc ¸a. Sgain, wsgain-cp and wsgain- gp: Novel gan methods for missing data imputation. In In- ternational Conference on Computational Science, pages 98-113. Springer, 2021.","title":"Sgain, wsgain-cp and wsgaingp: Novel gan methods for missing data imputation","authors":"Marcel Diogo Telmo Neves, Alberto Ganesh Naik, Proenc ¸a","year":"2021","venue":"ternational Conference on Computational Science","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Santos et al., 2019] Miriam Seoane Santos, Ricardo Car- doso Pereira, Adriana Fonseca Costa, Jastin Pompeu Soares, João Santos, and Pedro Henriques Abreu. Gener- ating synthetic missing data: A review by missing mecha- nism. IEEE Access, 7:11651-11667, 2019.","title":"Generating synthetic missing data: A review by missing mechanism","authors":"Miriam Seoane, Santos, Ricardo Cardoso Pereira, Adriana Fonseca Costa, Jastin Pompeu Soares, João Santos, Pedro Henriques Abreu","year":"2019","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Scheffer, 2002] Judi Scheffer. Dealing with missing data. 2002.","title":"Dealing with missing data","authors":"Judi Scheffer","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Stekhoven and Bühlmann, 2011] D. J. Stekhoven and P Bühlmann. Missforest -nonparametric missing value imputation for mixed-type data. 2011.","title":"Missforest -nonparametric missing value imputation for mixed-type data","authors":"D J Stekhoven, Bühlmann","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Wang et al., 2021] Yufeng Wang, Dan Li, Xiang Li, and Min Yang. Pc-gain: Pseudo-label conditional generative adversarial imputation networks for incomplete data. Neu- ral Networks, 141:395-403, 2021.","title":"Pc-gain: Pseudo-label conditional generative adversarial imputation networks for incomplete data","authors":"Yufeng Wang, Dan Li, Xiang Li, Min Yang","year":"2021","venue":"Neural Networks","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Williams, 2015] R Williams. Missing data part 1: Overview, traditional methods. university of notre dame, 2015.","title":"Missing data part 1: Overview, traditional methods","authors":"Williams","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yoon and Sull, 2020] Seongwook Yoon and Sanghoon Sull. Gamin: Generative adversarial multiple imputation net- work for highly missing data. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 8456-8464, 2020.","title":"Gamin: Generative adversarial multiple imputation network for highly missing data","authors":"Sull Yoon, Seongwook Yoon, Sanghoon Sull","year":"2020","venue":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yoon et al., 2018] Jinsung Yoon, James Jordon, and Mi- haela Schaar. Gain: Missing data imputation using gen- erative adversarial nets. In International conference on machine learning, pages 5689-5698. PMLR, 2018.","title":"Gain: Missing data imputation using generative adversarial nets","authors":"Yoon","year":"2018","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yu et al., 2016] Hsiang-Fu Yu, Nikhil Rao, and Inderjit S Dhillon. Temporal regularized matrix factorization for high-dimensional time series prediction. Advances in neu- ral information processing systems, 29, 2016.","title":"Temporal regularized matrix factorization for high-dimensional time series prediction","authors":"Hsiang-Fu Yu, Nikhil Rao, Inderjit S Dhillon","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yuan et al., 2022] Ye Yuan, Yong Zhang, Boyue Wang, Yuan Peng, Yongli Hu, and Baocai Yin. Stgan: Spatio- temporal generative adversarial network for traffic data imputation. IEEE Transactions on Big Data, 2022.","title":"Stgan: Spatiotemporal generative adversarial network for traffic data imputation","authors":"Ye Yuan, Yong Zhang, Boyue Wang, Yuan Peng, Yongli Hu, Baocai Yin","year":"2022","venue":"IEEE Transactions on Big Data","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2021] Weibin Zhang, Pulin Zhang, Ying- hao Yu, Xiying Li, Salvatore Antonio Biancardo, and Junyi Zhang. Missing data repairs for traffic flow with self-attention generative adversarial imputation net. IEEE Transactions on Intelligent Transportation Systems, 23(7):7919-7930, 2021.","title":"Missing data repairs for traffic flow with self-attention generative adversarial imputation net","authors":"Weibin Zhang, Pulin Zhang, Yinghao Yu, Xiying Li, Salvatore Antonio Biancardo, Junyi Zhang","year":"2021","venue":"IEEE Transactions on Intelligent Transportation Systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}