GNNsMiscalibrated
None
view repo
Graph Neural Networks (GNNs) have proven to be successful in many classification tasks, outperforming previous state-of-the-art methods in terms of accuracy. However, accuracy alone is not enough for high-stakes decision making. Decision makers want to know the likelihood that a specific GNN prediction is correct. For this purpose, obtaining calibrated models is essential. In this work, we analyze the calibration of state-of-the-art GNNs on multiple datasets. Our experiments show that GNNs can be calibrated in some datasets but also badly miscalibrated in others, and that state-of-the-art calibration methods are helpful but do not fix the problem.
READ FULL TEXT
Graphs play an important role in many applications. Recently, Graph Neur...
read it
Modern graph neural networks (GNNs) learn node embeddings through multil...
read it
Graph neural networks (GNNs) have achieved state-of-the-art performance ...
read it
Recently, Graph Neural Networks (GNNs) are trending in the machine learn...
read it
Graph Neural Networks (GNNs) have made significant advances on several
f...
read it
As the performance of computer systems stagnates due to the end of Moore...
read it
Recently there has been a significant effort to automate UV mapping, the...
read it
None
Comments
There are no comments yet.