Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation
This addresses a foundational limitation in set prediction for machine learning, offering a novel approach with significant performance gains.
The paper tackles the problem of set prediction models operating on multisets by introducing multiset-equivariance, showing that set-equivariant functions are insufficient, and improves the Deep Set Prediction Network with approximate implicit differentiation for better optimization. On CLEVR object property prediction, it improves state-of-the-art Slot Attention from 8% to 77% in a strict metric.
Most set prediction models in deep learning use set-equivariant operations, but they actually operate on multisets. We show that set-equivariant functions cannot represent certain functions on multisets, so we introduce the more appropriate notion of multiset-equivariance. We identify that the existing Deep Set Prediction Network (DSPN) can be multiset-equivariant without being hindered by set-equivariance and improve it with approximate implicit differentiation, allowing for better optimization while being faster and saving memory. In a range of toy experiments, we show that the perspective of multiset-equivariance is beneficial and that our changes to DSPN achieve better results in most cases. On CLEVR object property prediction, we substantially improve over the state-of-the-art Slot Attention from 8% to 77% in one of the strictest evaluation metrics because of the benefits made possible by implicit differentiation.