Data Imputation with Iterative Graph Reconstruction

TL;DR

This paper introduces IGRM, a novel graph-based data imputation method that models sample relations with friend networks, leading to significantly improved imputation accuracy on benchmark datasets.

Contribution

The paper proposes a new iterative graph reconstruction framework that models sample relations with friend networks, enhancing data imputation performance.

Findings

39.13% lower mean absolute error compared to baselines

Effective modeling of sample relations improves imputation accuracy

Outperforms existing methods on eight benchmark datasets

Abstract

Effective data imputation demands rich latent ``structure" discovery capabilities from ``plain" tabular data. Recent advances in graph neural networks-based data imputation solutions show their strong structure learning potential by directly translating tabular data as bipartite graphs. However, due to a lack of relations between samples, those solutions treat all samples equally which is against one important observation: ``similar sample should give more information about missing values." This paper presents a novel Iterative graph Generation and Reconstruction framework for Missing data imputation(IGRM). Instead of treating all samples equally, we introduce the concept: ``friend networks" to represent different relations among samples. To generate an accurate friend network with missing data, an end-to-end friend network reconstruction solution is designed to allow for continuous friend network optimization during imputation learning. The representation of the optimized friend network, in turn, is used to further optimize the data imputation process with differentiated message passing. Experiment results on eight benchmark datasets show that IGRM yields 39.13% lower mean absolute error compared with nine baselines and 9.04% lower than the second-best. Our code is available at https://github.com/G-AILab/IGRM.