Toaudit filteringinformation usersees frequent, "similarity" Suppose T (e.g., Suppose F generates Z of T when givenx0. RecallfromF complies F is decision-rob F isguaranteed ontheroleof 4.1 Guarantee Theorem 1.Consider(1).

Recent efforts have shown promising results in this direction by making use of depth-wiserecurrentnetworks.

A wide range of models have been proposed for Graph Generative Models, necessitating effective methods to evaluate their quality. So far, most techniques use either traditional metrics based onsubgraph counting, ortherepresentations of randomly initialized Graph Neural Networks (GNNs). We propose using representations from contrastively trained GNNs, rather than random GNNs, and show this gives more reliable evaluation metrics. Neither traditional approaches nor GNN-based approaches dominate the other,however: we giveexamples of graphs that each approach is unable to distinguish. We demonstrate that Graph Substructure Networks (GSNs), which in a way combine both approaches, are better at distinguishing the distances between graph datasets.

TheIRLsettingisremarkably useful for automated control, in situations where the reward function is difficult to specify manually or as a means to extract agent preference.