Better Set Representations For Relational Reasoning

Understand

Incorporating relational reasoning into neural networks has greatly expanded their capabilities and scope.

• One defining trait of relational reasoning is that it operates on a set of entities, as opposed to standard vector representations.
• Existing end-to-end approaches typically extract entities from inputs by directly interpreting the latent feature representations as a set.
• We show that these approaches do not respect set permutational invariance and thus have fundamental representational limitations.