Drop the mask! GAMM-A Taxonomy for Graph Attributes Missing Mechanisms
This addresses missing data challenges for graph-based machine learning applications, but it appears incremental as it extends existing taxonomies to graphs.
The authors tackled the problem of missing data in attributed graphs by proposing GAMM, a taxonomy that links missingness probability to node attributes and graph structure, and they found that state-of-the-art imputation methods significantly struggle with these graph-aware scenarios.
Exploring missing data in attributed graphs introduces unique challenges beyond those found in tabular datasets. In this work, we extend the taxonomy for missing data mechanisms to attributed graphs by proposing GAMM (Graph Attributes Missing Mechanisms), a framework that systematically links missingness probability to both node attributes and the underlying graph structure. Our taxonomy enriches the conventional definitions of masking mechanisms by introducing graph-specific dependencies. We empirically demonstrate that state-of-the-art imputation methods, while effective on traditional masks, significantly struggle when confronted with these more realistic graph-aware missingness scenarios.