mlsanityData to 7 Oct 2026

A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systems

arXiv 2401.10300 ↗First posted 18 Jan 2024cs.MA cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Emergence, a global property of complex adaptive systems (CASs) constituted by interactive agents, is prevalent in real-world dynamic systems, e.g., network-level traffic congestions. Detecting its formation and evaporation helps to monitor the state of a system, allowing to issue a warning signal for harmful emergent phenomena. Since there is no centralized controller of CAS, detecting emergence based on each agent's local observation is desirable but challenging. Existing works are unable to capture emergence-related spatial patterns, and fail to model the nonlinear relationships among agents. This paper proposes a hierarchical framework with spatio-temporal consistency learning to solve these two problems by learning the system representation and agent representations, respectively. Spatio-temporal encoders composed of spatial and temporal transformers are designed to capture agents' nonlinear relationships and the system's complex evolution. Agents' and the system's representations are learned to preserve the spatio-temporal consistency by minimizing the spatial and temporal dissimilarities in a self-supervised manner in the latent space. Our method achieves more accurate detection than traditional methods and deep learning methods on three datasets with well-known yet hard-to-detect emergent behaviors. Notably, our hierarchical framework is generic in incorporating other deep learning methods for agent-level and system-level detection.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 34 of its 100 references that are in the map. First posted on arXiv 18 Jan 2024.

Builds on

34 of 100 references.

References · 34

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  6. 2021Graph Neural Network-Based Anomaly Detection in Multivariate Time Seriescited by 300
  7. 2020Towards Deeper Graph Neural Networkscited by 296
  8. 2021A Comprehensive Survey on Graph Anomaly Detection with Deep Learningcited by 230
  9. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  10. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 171
  11. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  12. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 123
22 more
  1. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 98
  2. 2023Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospectscited by 97
  3. 2022Self-Supervised Learning for Videos: A Surveycited by 85
  4. 2021Understanding Pooling in Graph Neural Networkscited by 69
  5. 2020An Evaluation of Change Point Detection Algorithmscited by 62
  6. 2020Time Series Change Point Detection with Self-Supervised Contrastive Predictive Codingcited by 58
  7. 2020On Using Classification Datasets to Evaluate Graph-Level Outlier Detection: Peculiar Observations and New Insightscited by 53
  8. 2022Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunitiescited by 52
  9. 2022Raising the Bar in Graph-level Anomaly Detectioncited by 45
  10. 2019Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networkscited by 40
  11. 2021When Do Contrastive Learning Signals Help Spatio-Temporal Graph Forecasting?cited by 36
  12. 2020Laplacian Change Point Detection for Dynamic Graphscited by 25
  13. 2023Automated Spatio-Temporal Graph Contrastive Learningcited by 24
  14. 2022A Survey of Graph-based Deep Learning for Anomaly Detection in Distributed Systemscited by 20
  15. 2023Permutation Equivariant Graph Framelets for Heterophilous Graph Learningcited by 19
  16. 2023Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detectioncited by 17
  17. 2021Towards Graph Self-Supervised Learning with Contrastive Adjusted Zoomingcited by 15
  18. 2021Learnable Dynamic Temporal Pooling for Time Series Classificationcited by 13
  19. 2017Fast Change Point Detection on Dynamic Social Networkscited by 11
  20. 2023Laplacian Change Point Detection for Single and Multi-view Dynamic Graphscited by 7
  21. 2017Agent-based computing from multi-agent systems to agent-based Models: a visual surveycited by 4
  22. 2022Graph similarity learning for change-point detection in dynamic networkscited by 4

Built on by

Not cited yet.