Skip to yearly menu bar Skip to main content


Poster

Catalytic Role Of Noise And Necessity Of Inductive Biases In The Emergence Of Compositional Communication

Łukasz Kuciński · Tomasz Korbak · Paweł Kołodziej · Piotr Miłoś

Keywords: [ Graph Learning ] [ Deep Learning ]


Abstract:

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.

Chat is not available.