Improved Dynamic Graph Learning through Fault-Tolerant Sparsification
Graph sparsification has been used to improve the computational cost of learning over graphs, e.g., Laplacian-regularized estimation and graph semi-supervised learning (SSL). However, when graphs vary over time, repeated sparsification requires polynomial order computational cost per update. We propose a new type of graph sparsification namely fault-tolerant (FT) sparsification to significantly reduce the cost to only a constant. Then the computational cost of subsequent graph learning tasks can be significantly improved with limited loss in their accuracy. In particular, we give theoretical analyze to upper bound the loss in the accuracy of the subsequent Laplacian-regularized estimation and graph SSL, due to the FT sparsification. In addition, FT spectral sparsification can be generalized to FT cut sparsification, for cut-based graph learning. Extensive experiments have confirmed the computational efficiencies and accuracies of the proposed methods for learning on dynamic graphs.
Authors:
; ; ; ;
Award ID(s):
Publication Date:
NSF-PAR ID:
10107148
Journal Name:
Proceedings of the 36th International Conference on Machine Learning
Volume:
97
Page Range or eLocation-ID:
7624-7633
4. Graph compression or sparsification is a basic information-theoretic and computational question. A major open problem in this research area is whether $(1+\epsilon)$-approximate cut-preserving vertex sparsifiers with size close to the number of terminals exist. As a step towards this goal, we initiate the study of a thresholded version of the problem: for a given parameter $c$, find a smaller graph, which we call \emph{connectivity-$c$ mimicking network}, which preserves connectivity among $k$ terminals exactly up to the value of $c$. We show that connectivity-$c$ mimicking networks of size $O(kc^4)$ exist and can be found in time $m(c\log n)^{O(c)}$. We also givemore »