Towards Graph Representation Learning in Emergent Communication

24 Jan 2020  ·  Agnieszka Słowik, Abhinav Gupta, William L. Hamilton, Mateja Jamnik, Sean B. Holden ·

Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces). In order to communicate, we flatten the complex representation of entities and their attributes into a single word or a sentence. In this paper we use graph convolutional networks to support the evolution of language and cooperation in multi-agent systems. Motivated by an image-based referential game, we propose a graph referential game with varying degrees of complexity, and we provide strong baseline models that exhibit desirable properties in terms of language emergence and cooperation. We show that the emerged communication protocol is robust, that the agents uncover the true factors of variation in the game, and that they learn to generalize beyond the samples encountered during training.

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.