Reconstruction of Pairwise Interactions using Energy-Based Models

Abstract

Pairwise models like the Ising model or the generalized Potts model have found many successful applications in fields like physics, biology, and economics. Closely connected is the problem of inverse statistical mechanics, where the goal is to infer the parameters of such models given observed data. An open problem in this field is the question of how to train these models in the case where the data contain additional higher-order interactions that are not present in the pairwise model. In this work, we propose an approach based on Energy-Based Models and pseudolikelihood maximization to address these complications: we show that hybrid models, which combine a pairwise model and a neural network, can lead to significant improvements in the reconstruction of pairwise interactions. We show these improvements to hold consistently when compared to a standard approach using only the pairwise model and to an approach using only a neural network. This is in line with the general idea that simple interpretable models and complex black-box models are not necessarily a dichotomy: interpolating these two classes of models can allow to keep some advantages of both.

References in corpus (15)

• Array Programming with NumPy
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Improved contact prediction in proteins: Using pseudolikelihoods to infer Potts models
• Inverse Statistical Physics of Protein Sequences: A Key Issues Review
• Solving Statistical Mechanics Using Variational Autoregressive Networks
• The Ising Model for Neural Data: Model Quality and Approximate Methods for Extracting Functional Connectivity
• Social applications of two-dimensional Ising models
• Implicit Generation and Generalization in Energy-Based Models
• Improving contact prediction along three dimensions
• How to Train Your Energy-Based Models
• Deep Learning the Ising Model Near Criticality
• The statistical mechanics of Twitter
• Learning of Discrete Graphical Models with Neural Networks
• Physics and Financial Economics (1776-2014): Puzzles, Ising and Agent-Based models