Timezone: »

 
Poster
Interpretable agent communication from scratch (with a generic visual processor emerging on the side)
Roberto Dessi · Eugene Kharitonov · Baroni Marco

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @ Virtual
in Poster Session 1 »

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.

Keywords: Deep Learning · Self-Supervised Learning · Interpretability

Author Information

Roberto Dessi (Facebook)
Eugene Kharitonov (Facebook AI)
Baroni Marco (Facebook)

More from the Same Authors