2020/02/04 by Słowik, Agnieszka, Gupta, Abhinav, Hamilton, William L. +3
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multiagent Systems (cs.MA)
paper · doi:10.48550/arxiv.2002.01335
In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence. We investigate the impact of representation learning in artificial agents by developing graph referential games. We empirically show that agents parametrized by graph neural networks develop a more compositional language compared to bag-of-words and sequence models, which allows them to systematically generalize to new combinations of familiar features.