Adaptive Message Passing: A General Framework to Mitigate Oversmoothing, Oversquashing, and Underreaching

arXiv:2312.16560v2 Announce Type: replace
Abstract: Long-range interactions are essential for the correct description of complex systems in many scientific fields. The price to pay for including them in the calculations, however, is a dramatic increase in the overall computational costs. Recently, deep graph networks have been employed as efficient, data-driven surrogate models for predicting properties of complex systems represented as graphs. These models rely on a local and iterative message passing strategy that should, in principle, capture long-range information without …

abstract arxiv complex systems computational costs cs.lg fields framework general graph however interactions networks price scientific systems them type