Neural Non-additive Utility Aggregation

Abstract

Neural architectures for set regression problems aim at learning representations such that good predictions can be made based on the learned representations. This strategy, however, ignores the fact that meaningful intermediate results might be helpful to perform well. We study two new architectures that explicitly model latent intermediate utilities and use non-additive utility aggregation to estimate the set utility based on the latent utilities. We evaluate the new architectures with visual and textual datasets, which have non-additive set utilities due to redundancy and synergy effects. We find that the new architectures perform substantially better in this setup.

Tasks

Reproductions