Measuring Dependencies between Biological Signals with Self-supervision, and its Limitations
By: Evangelos Sariyanidi , John D. Herrington , Lisa Yankowitz and more
Potential Business Impact:
Finds hidden connections in body signals.
Measuring the statistical dependence between observed signals is a primary tool for scientific discovery. However, biological systems often exhibit complex non-linear interactions that currently cannot be captured without a priori knowledge regarding the nature of dependence. We introduce a self-supervised approach, concurrence, which is inspired by the observation that if two signals are dependent, then one should be able to distinguish between temporally aligned vs. misaligned segments extracted from them. Experiments with fMRI, physiological and behavioral signals show that, to our knowledge, concurrence is the first approach that can expose relationships across such a wide spectrum of signals and extract scientifically relevant differences without ad-hoc parameter tuning or reliance on a priori information, providing a potent tool for scientific discoveries across fields. However, dependencies caused by extraneous factors remain an open problem, thus researchers should validate that exposed relationships truly pertain to the question(s) of interest.
Similar Papers
Contrastive Learning for Correlating Network Incidents
Networking and Internet Architecture
Finds internet problems faster by learning from past issues.
Symbol-Temporal Consistency Self-supervised Learning for Robust Time Series Classification
Machine Learning (CS)
Learns health patterns even with messy data.
Canonical Tail Dependence for Soft Extremal Clustering of Multichannel Brain Signals
Machine Learning (Stat)
Finds brain signals that predict seizures.