mlsanityData to 14 Oct 2026

Finding emergence in data by maximizing effective information

arXiv 2308.09952 ↗First posted 19 Aug 2023physics.soc-ph cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Quantifying emergence and modeling emergent dynamics in a data-driven manner for complex dynamical systems is challenging due to the lack of direct observations at the micro-level. Thus, it's crucial to develop a framework to identify emergent phenomena and capture emergent dynamics at the macro-level using available data. Inspired by the theory of causal emergence (CE), this paper introduces a machine learning framework to learn macro-dynamics in an emergent latent space and quantify the degree of CE. The framework maximizes effective information, resulting in a macro-dynamics model with enhanced causal effects. Experimental results on simulated and real data demonstrate the effectiveness of the proposed framework. It quantifies degrees of CE effectively under various conditions and reveals distinct influences of different noise types. It can learn a one-dimensional coarse-grained macro-state from fMRI data, to represent complex neural activities during movie clip viewing. Furthermore, improved generalization to different test environments is observed across all simulation data.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 21 of its 69 references that are in the map. First posted on arXiv 19 Aug 2023.

Builds on

21 of 69 references.

References · 21

  1. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  2. 2016Density estimation using Real NVPcited by 2,042
  3. 2015Weight Uncertainty in Neural Networkscited by 554
  4. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  5. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 436
  6. 2018Neural Relational Inference for Interacting Systemscited by 339
  7. 2020Invariant Causal Prediction for Block MDPscited by 105
  8. 2020Multiscale Simulations of Complex Systems by Learning their Effective Dynamicscited by 86
  9. 2020Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximatorscited by 85
  10. 2022Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognitioncited by 71
  11. 2014Machine Learning for Neuroimaging with Scikit-Learncited by 70
  12. 2021Data-driven discovery of intrinsic dynamicscited by 45
9 more
  1. 2022From Statistical to Causal Learningcited by 40
  2. 2020Universal Approximation Property of Neural Ordinary Differential Equationscited by 32
  3. 2016When the map is better than the territorycited by 17
  4. 2020Reconciling emergences: An information-theoretic approach to identify causal emergence in multivariate datacited by 16
  5. 2019The emergence of informative higher scales in complex networkscited by 4
  6. 2019Finding the right scale of a network: Efficient identification of causal emergence through spectral clusteringcited by 4
  7. 2020Examining the causal structures of deep neural networks using information theorycited by 3
  8. 2022Neural Information Squeezer for Causal Emergencecited by 3
  9. 2020Independent Gaussian Distributions Minimize the Kullback-Leibler (KL) Divergence from Independent Gaussian Distributionscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 0; 2025: 1; 2026: 1.

4 papers.

  1. 2023Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiescited by 3
  2. 2023Data driven modeling for self-similar dynamicscited by 0
  3. 2025A Framework for Analyzing Abnormal Emergence in Service Ecosystems Through LLM-based Agent Intention Miningcited by 0
  4. 2026Partial Effective Information Decomposition for Synergistic Causalitycited by 0