The use of a global population can lead to potentially misleading results when local model behaviour is of interest. Hence we consider the formulation of neighbourhood reference distributions that improve the local interpretability of Shapley values.

Learning has become a core component of the modern information systems we increasingly rely upon to select job candidates, analyze medical data, and control "smart" applications (home, grid, city).

Video recognition is an important problem with many potential applications.

To better understand this trade-off, we observe that sparse and low-rank approximations excel in different regimes, determined by the softmax temperature in attention, and sparse + low-rank can outperform each individually.