How social reinforcement learning can lead to metastable polarisation and the voter model
- URL: http://arxiv.org/abs/2406.07993v1
- Date: Wed, 12 Jun 2024 08:38:47 GMT
- Title: How social reinforcement learning can lead to metastable polarisation and the voter model
- Authors: Benedikt V. Meylahn, Janusz M. Meylahn,
- Abstract summary: We show that polarization is stable when agents form their opinions using reinforcement learning.
By constructing a link between the reinforcement learning model and the voter model, we argue that the observed polarization is metastable.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Previous explanations for the persistence of polarization of opinions have typically included modelling assumptions that predispose the possibility of polarization (e.g.\ repulsive interactions). An exception is recent research showing that polarization is stable when agents form their opinions using reinforcement learning. We show that the polarization observed in this model is not stable, but exhibits consensus asymptotically with probability one. By constructing a link between the reinforcement learning model and the voter model, we argue that the observed polarization is metastable. Finally, we show that a slight modification in the learning process of the agents changes the model from being non-ergodic to being ergodic. Our results show that reinforcement learning may be a powerful method for modelling polarization in opinion dynamics, but that the tools appropriate for analysing such models crucially depend on the properties of the resulting systems. Properties which are determined by the details of the learning process.
Related papers
- MAGIC: Modular Auto-encoder for Generalisable Model Inversion with Bias Corrections [0.19241821314180374]
We replace the decoder stage of a standard autoencoder with a physical model followed by a bias-correction layer.
This generalisable approach simultaneously inverts the model and corrects its biases in an end-to-end manner without making strong assumptions about the nature of the biases.
Our method matches or surpasses results from classical approaches without requiring biases to be explicitly filtered out.
arXiv Detail & Related papers (2024-05-29T10:11:10Z) - Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
We propose to expose captured knowledge in the form of a directed acyclic causal graph.
We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs.
The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
arXiv Detail & Related papers (2023-09-30T20:59:42Z) - Guide the Learner: Controlling Product of Experts Debiasing Method Based
on Token Attribution Similarities [17.082695183953486]
A popular workaround is to train a robust model by re-weighting training examples based on a secondary biased model.
Here, the underlying assumption is that the biased model resorts to shortcut features.
We introduce a fine-tuning strategy that incorporates the similarity between the main and biased model attribution scores in a Product of Experts loss function.
arXiv Detail & Related papers (2023-02-06T15:21:41Z) - The drivers of online polarization: fitting models to data [0.0]
echo chamber effect and opinion polarization may be driven by several factors including human biases in information consumption and personalized recommendations produced by feed algorithms.
Until now, studies have mainly used opinion dynamic models to explore the mechanisms behind the emergence of polarization and echo chambers.
We provide a method to numerically compare the opinion distributions obtained from simulations with those measured on social media.
arXiv Detail & Related papers (2022-05-31T17:00:41Z) - Explain, Edit, and Understand: Rethinking User Study Design for
Evaluating Model Explanations [97.91630330328815]
We conduct a crowdsourcing study, where participants interact with deception detection models that have been trained to distinguish between genuine and fake hotel reviews.
We observe that for a linear bag-of-words model, participants with access to the feature coefficients during training are able to cause a larger reduction in model confidence in the testing phase when compared to the no-explanation control.
arXiv Detail & Related papers (2021-12-17T18:29:56Z) - Estimation of Bivariate Structural Causal Models by Variational Gaussian
Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
Causal mechanisms can be described by structural causal models.
One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
arXiv Detail & Related papers (2021-09-06T14:52:58Z) - Disentangling Observed Causal Effects from Latent Confounders using
Method of Moments [67.27068846108047]
We provide guarantees on identifiability and learnability under mild assumptions.
We develop efficient algorithms based on coupled tensor decomposition with linear constraints to obtain scalable and guaranteed solutions.
arXiv Detail & Related papers (2021-01-17T07:48:45Z) - Why do classifier accuracies show linear trends under distribution
shift? [58.40438263312526]
accuracies of models on one data distribution are approximately linear functions of the accuracies on another distribution.
We assume the probability that two models agree in their predictions is higher than what we can infer from their accuracy levels alone.
We show that a linear trend must occur when evaluating models on two distributions unless the size of the distribution shift is large.
arXiv Detail & Related papers (2020-12-31T07:24:30Z) - Learning from others' mistakes: Avoiding dataset biases without modeling
them [111.17078939377313]
State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task.
Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available.
We show a method for training models that learn to ignore these problematic correlations.
arXiv Detail & Related papers (2020-12-02T16:10:54Z) - A theory of independent mechanisms for extrapolation in generative
models [20.794692397859755]
Generative models can be trained to emulate complex empirical data, but are they useful to make predictions in the context of previously unobserved environments?
We develop a theoretical framework to address this challenging situation by defining a weaker form of identifiability, based on the principle of independence of mechanisms.
We demonstrate on toy examples that classical gradient descent can hinder the model's extrapolation capabilities, suggesting independence of mechanisms should be enforced explicitly during training.
arXiv Detail & Related papers (2020-04-01T01:01:43Z) - ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on
Nonlinear ICA [11.919315372249802]
We consider the identifiability theory of probabilistic models.
We show that our model can be used for the estimation of the components in the framework of Independently Modulated Component Analysis.
arXiv Detail & Related papers (2020-02-26T14:43:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.