no code implementations • 6 Nov 2023 • Behrooz Tahmasebi, Stefanie Jegelka
Our results indicate a two-fold gain: (1) reducing the sample complexity by a multiplicative factor corresponding to the group size (for finite groups) or the normalized volume of the quotient space (for groups of positive dimension); (2) improving the exponent in the convergence rate (for groups of positive dimension).
no code implementations • 29 Sep 2021 • Behrooz Tahmasebi, Stefanie Jegelka
Our theoretical results imply constraints on the model for exploiting random node IDs, and, conversely, insights into the tolerance of a given model class for retaining discrimination with perturbations of node attributes.
no code implementations • 1 Jan 2021 • Behrooz Tahmasebi, Stefanie Jegelka
While Graph Neural Networks (GNNs) have become increasingly popular architectures for learning with graphs, recent works have revealed important shortcomings in their expressive power.
no code implementations • 6 Dec 2020 • Behrooz Tahmasebi, Derek Lim, Stefanie Jegelka
While message passing Graph Neural Networks (GNNs) have become increasingly popular architectures for learning with graphs, recent works have revealed important shortcomings in their expressive power.