TY - GEN
T1 - Convolution-consistent collective matrix completion
AU - Liu, Xu
AU - He, Jingrui
AU - Duddy, Sam
AU - O'Sullivan, Liz
N1 - Funding Information:
to the ideal order (blue stars). The exception happens in the data set with ID 7 as the data volume is relatively small. In addition to the order estimation, we verify the assumption in Problem 1 that larger K does not signify the authentic cross-matrix information. As shown in Fig. 3, the completion performance declines as the MSE value bounces back after a certain point of the increasing filter order, as the cross-matrix information being impaired when incorporating the nodes far away from the neighborhood. 4 CONCLUSION In this paper, we have proposed a novel multi-view graph convolution framework (C4) for collective matrix completion. We make the first effort to decode the essential cross-matrix information in the graph spectral domain and quantify the matrices’ interactive impacts. Experimental results on ten real-world data sets demonstrate the effectiveness of C4 as compared to state-of-the-art methods. ACKNOWLEDGEMENT This work is supported by National Science Foundation under Grant No. IIS-1552654 and Grant No. IIS-1813464, the U.S. Department of Homeland Security under Grant Award Number 17STQAC00001-02-00, and an IBM Faculty Award. The views and conclusions are those of the authors and should not be interpreted as representing the official policies of the funding agencies or the government.
Publisher Copyright:
© 2019 Association for Computing Machinery.
PY - 2019/11/3
Y1 - 2019/11/3
N2 - Collective matrix completion refers to the problem of simultaneously predicting the missing entries in multiple matrices by leveraging the cross-matrix information. It finds abundant applications in various domains such as recommender system, dimensionality reduction, and image recovery. Most of the existing work represents the cross-matrix information in a shared latent structure constrained by the Euclidean-based pairwise similarity, which may fail to capture the nonlinear relationship of the data. To address this problem, in this paper, we propose a new collective matrix completion framework, named C4, which uses the graph spectral filters to capture the non-Euclidean cross-matrix information. To the best of our knowledge, this is the first effort to represent the cross-matrix information in the graph spectral domain. We benchmark our model against 8 recent models on 10 real-world data sets, and our model outperforms state-of-the-art methods in most tasks.
AB - Collective matrix completion refers to the problem of simultaneously predicting the missing entries in multiple matrices by leveraging the cross-matrix information. It finds abundant applications in various domains such as recommender system, dimensionality reduction, and image recovery. Most of the existing work represents the cross-matrix information in a shared latent structure constrained by the Euclidean-based pairwise similarity, which may fail to capture the nonlinear relationship of the data. To address this problem, in this paper, we propose a new collective matrix completion framework, named C4, which uses the graph spectral filters to capture the non-Euclidean cross-matrix information. To the best of our knowledge, this is the first effort to represent the cross-matrix information in the graph spectral domain. We benchmark our model against 8 recent models on 10 real-world data sets, and our model outperforms state-of-the-art methods in most tasks.
UR - http://www.scopus.com/inward/record.url?scp=85075444223&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85075444223&partnerID=8YFLogxK
U2 - 10.1145/3357384.3358111
DO - 10.1145/3357384.3358111
M3 - Conference contribution
AN - SCOPUS:85075444223
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 2209
EP - 2212
BT - CIKM 2019 - Proceedings of the 28th ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 28th ACM International Conference on Information and Knowledge Management, CIKM 2019
Y2 - 3 November 2019 through 7 November 2019
ER -