Physical System for Non Time Sequence Data

TL;DR

This paper introduces a novel method linking neural network Jacobians to causal structure learning in physical systems, enabling causal inference from neural ODEs with reduced complexity and enforced acyclicity.

Contribution

It extends Jacobian-based causal structure learning to physical systems using neural ODEs, incorporating acyclicity constraints to improve efficiency and causal interpretability.

Findings

Successfully reads causal structure from neural ODE functions

Enforces acyclicity on continuous adjacency matrices

Reduces computational complexity in causal graph search

Abstract

We propose a novelty approach to connect machine learning to causal structure learning by jacobian matrix of neural network w.r.t. input variables. In this paper, we extend the jacobian-based approach to physical system which is the method human explore and reason the world and it is the highest level of causality. By functions fitting with Neural ODE, we can read out causal structure from functions. This method also enforces a important acylicity constraint on continuous adjacency matrix of graph nodes and significantly reduce the computational complexity of search space of graph.