Data Imputation with Iterative Graph Reconstruction

arXiv:2212.02810v2 Announce Type: replace
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 …

arxiv cs.lg data graph imputation iterative type