Taking advantage of an analogy between Transformer stages and the evolution of a dynamical system of multiple interacting particles, we formulate a temporal evolution scheme,TransEvolve, to bypass costly dot-product attention over multiple stacked layers.

MIL has become particularly popular in histopathology, where gigapixel microscopy slides are cut into patches representing small tissue regions.

Learning representations of sets of nodes in a graph is crucial for applications ranging from node-role discovery to link prediction and molecule classification.