Submission

The high-level idea of MGD is to measure the differences between many pairs of marginal tables.  For each pair, the difference is measured by a newly proposed Approximate Earth Mover Cost, which is inspired by earth-mover distance and considers both semantic meanings of attribute values and the noisy nature of the synthesized dataset.  While the current challenge focuses on temporal map data, MGD is designed for relational datasets in general, and can be naturally applied to temporal map data.