Causal Attention to Exploit Transient Emergence of Causal EffectDownload PDF

Published: 01 Feb 2023, Last Modified: 13 Feb 2023Submitted to ICLR 2023Readers: Everyone
Keywords: causal attention mechanism, coupling-drive, sparse causal effect, neural dynamics, causal network reconstruction
TL;DR: We propose the causal attention mechanism for a class of causal network reconstruction tasks.
Abstract: We propose a causal reasoning mechanism called $\textit{causal attention}$ that can improve performance of machine learning models on a class of causal inference tasks by revealing the generation process behind the observed data. We consider the problem of reconstructing causal networks (e.g., biological neural networks) connecting large numbers of variables (e.g., nerve cells), of which evolution is governed by nonlinear dynamics consisting of weak coupling-drive (i.e., causal effect) and strong self-drive (dominants the evolution). The core difficulty is sparseness of causal effect that emerges (the coupling force is significant) only momentarily and otherwise remains dormant in the neural activity sequence. $\textit{Causal attention}$ is designed to guide the model to make inference focusing on the critical regions of time series data where causality may manifest. Specifically, attention coefficients are assigned autonomously by a neural network trained to maximise the Attention-extended Transfer Entropy, which is a novel generalization of the iconic transfer entropy metric. Our results show that, without any prior knowledge of dynamics, $\textit{causal attention}$ explicitly identifies areas where the strength of coupling-drive is distinctly greater than zero. This innovation substantially improves reconstruction performance for both synthetic and real causal networks using data generated by neuronal models widely used in neuroscience.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )
Supplementary Material: zip
12 Replies