Neural Information Squeezer for Causal Emergence

TL;DR

This paper introduces Neural Information Squeezer, a machine learning framework that automatically discovers optimal coarse-graining strategies and macro-dynamics to identify causal emergence in Markovian systems from time series data.

Contribution

It presents a novel neural network-based method that decomposes coarse-graining into information conversion and dropping, enabling analytical insights and automatic detection of causal emergence.

Findings

Successfully extracts macro-dynamics and causal emergence from example systems.

Provides analytical expressions for effective information of macro-dynamics.

Demonstrates the framework's ability to identify causal emergence in data.

Abstract

The classic studies of causal emergence have revealed that in some Markovian dynamical systems, far stronger causal connections can be found on the higher-level descriptions than the lower-level of the same systems if we coarse-grain the system states in an appropriate way. However, identifying this emergent causality from the data is still a hard problem that has not been solved because the correct coarse-graining strategy can not be found easily. This paper proposes a general machine learning framework called Neural Information Squeezer to automatically extract the effective coarse-graining strategy and the macro-state dynamics, as well as identify causal emergence directly from the time series data. By decomposing a coarse-graining operation into two processes: information conversion and information dropping out, we can not only exactly control the width of the information channel, but also can derive some important properties analytically including the exact expression of the effective information of a macro-dynamics. We also show how our framework can extract the dynamics on different levels and identify causal emergence from the data on several exampled systems.