Timezone: »

 
Poster
Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication
Łukasz Kuciński · Tomasz Korbak · Paweł Kołodziej · Piotr Miłoś

Thu Dec 09 12:30 AM -- 02:00 AM (PST) @
in Poster Session 5 »

Communication is compositional if complex signals can be represented as a combination of simpler subparts. In this paper, we theoretically show that inductive biases on both the training framework and the data are needed to develop a compositional communication. Moreover, we prove that compositionality spontaneously arises in the signaling games, where agents communicate over a noisy channel. We experimentally confirm that a range of noise levels, which depends on the model and the data, indeed promotes compositionality. Finally, we provide a comprehensive study of this dependence and report results in terms of recently studied compositionality metrics: topographical similarity, conflict count, and context independence.

Keywords: Deep Learning · Graph Learning

Author Information

Łukasz Kuciński (Polish Academy of Sciences)
Tomasz Korbak (University of Sussex)
Paweł Kołodziej (Google)
Piotr Miłoś (Polish Academy of Sciences, University of Oxford)

More from the Same Authors