Neural networkmodels areknowntoreinforce hidden databiases, making them unreliable and difficult to interpret. We seek to build models that'know whatthey do not know' by introducing inductive biases in the function space.

We study the problem of learning a linear model to set the reserve price in an auction, given contextual information, in order to maximize expected revenue fromtheseller side.

We present the T emporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs.