Set2Set
A permutation-invariant neural network aggregation mechanism for set inputs that iteratively aggregates information from set elements through attention mechanisms, commonly used in graph representation learning.
Timeline (last 90 days)
A learnable permutation-invariant graph context aggregation mechanism (implemented with weighted averaging and Set2Set) achieved the largest improvement, about 0.9 percentage points, on the CVRP100 to CVRP20 transfer.
Set2Set is a permutation-invariant graph aggregation model that performs weighted summation over set elements through an iterative attention mechanism, adaptively capturing element importance.
All Facts (2)
A learnable permutation-invariant graph context aggregation mechanism (implemented with weighted averaging and Set2Set) achieved the largest improvement, about 0.9 percentage points, on the CVRP100 to CVRP20 transfer.
50%UnverifiedSet2Set is a permutation-invariant graph aggregation model that performs weighted summation over set elements through an iterative attention mechanism, adaptively capturing element importance.
50%