2021/06/08 by Roberto Dessì, Eugene Kharitonov, Dessì, Roberto +3 · 9 citations
Computer Science · Engineering · #Advanced Memory and Neural Computing #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Artificial intelligence #Computation and Language (cs.CL) #Computer science #Deep learning #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Field (mathematics) #Identification (biology) #Machine Learning (cs.LG) #Machine learning #Multiagent Systems (cs.MA) #Object (grammar) #Protocol (science) #Referent #Scratch #cs.AI #cs.CL #cs.LG #cs.MA
paper · pdf · doi:10.48550/arxiv.2106.04258
published in arXiv (Cornell University) (Cornell University) · Accepted at NeurIPS 2021
openalex publication_date 2021/06/08 · arxiv created 2021/10/15 · arxiv updated 2021/10/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
As deep networks begin to be deployed as autonomous agents, the issue of how they can communicate with each other becomes important. Here, we train two deep nets from scratch to perform realistic referent identification through unsupervised emergent communication. We show that the largely interpretable emergent protocol allows the nets to successfully communicate even about object types they did not see at training time. The visual representations induced as a by-product of our training regime, moreover, show comparable quality, when re-used as generic visual features, to a recent self-supervised learning model. Our results provide concrete evidence of the viability of (interpretable) emergent deep net communication in a more realistic scenario than previously considered, as well as establishing an intriguing link between this field and self-supervised visual learning.