The solid curve in the top panel is the optimal ROC curve. The dashed straight line in the bottom panel is the linear piece that can not be recovered by the weighted method directly. However, after connecting the points linearly, the optimal ROC curve can be recovered.

We formally introduce the notion of optimal ROC curve over a general model space.

Despite the remarkable success of graph neural networks (GNNs) for graph representation learning, they are generally built on the (unreliable) i.i.d.

We attempted to find such directions by running the following type of attack. In Figure 2 GOOD also stands out as having low confidence in all directions that we studied. However, there is no guarantee that GOOD does not also get in some direction asymptotically overconfident. Each convolu-tional layer is directly followed by a ReLU. In Section 2.1 we describe semi-joint training of We see that the AUCs of ProoD-S are almost identical to those of OE.

We first propose a generic dirty-label attack for supervised classification algorithms. We then propose an optimization-based clean-label attack in the transfer learning scenario, whereby the poisoning samples are correctly labeled and look "natural" to evade human moderation.

Accurate intraoperative diagnosis is essential for providing safe and effective care during brain tumor surgery.