Loss Functions for Multiset Prediction

Abstract

We study the problem of multiset prediction. The goal of multiset prediction is to train a predictor that maps an input to a multiset consisting of multiple items. Unlike existing problems in supervised learning, such as classification, ranking and sequence generation, there is no known order among items in a target multiset, and each item in the multiset may appear more than once, making this problem extremely challenging. In this paper, we propose a novel multiset loss function by viewing this problem from the perspective of sequential decision making. The proposed multiset loss function is empirically evaluated on two families of datasets, one synthetic and the other real, with varying levels of difficulty, against various baseline loss functions including reinforcement learning, sequence, and aggregated distribution matching loss functions. The experiments reveal the effectiveness of the proposed loss function over the others.

NIPS 2018

Cited by in corpus (8)

• Object-Centric Learning with Slot Attention
• FSPool: Learning Set Representations with Featurewise Sort Pooling
• Neural Language Generation: Formulation, Methods, and Evaluation
• Information Leakage in Embedding Models
• Elucidating image-to-set prediction: An analysis of models, losses and datasets
• Learning to Represent and Predict Sets with Deep Neural Networks
• Sequential Graph Dependency Parser
• Cost-Sensitive Training for Autoregressive Models