Modeling Conditional Dependencies in Multiagent Trajectories

Research output: Journal contributionsConference article in journalResearchpeer-review

Standard

Modeling Conditional Dependencies in Multiagent Trajectories. / Rudolph, Yannick; Brefeld, Ulf.
In: Proceedings of Machine Learning Research, Vol. 151, 2022, p. 10518-10533.

Research output: Journal contributionsConference article in journalResearchpeer-review

Harvard

APA

Vancouver

Bibtex

@article{f7a4f00425e0440d9fc2d7ab5bcf0b38,
title = "Modeling Conditional Dependencies in Multiagent Trajectories",
abstract = "We study modeling joint densities over sets of random variables (next-step movements of multiple agents) which are conditioned on aligned observations (past trajectories). For this setting, we propose an autoregressive approach to model intra-timestep dependencies, where distributions over joint movements are represented by autoregressive factorizations. In our approach, factors are randomly ordered and estimated with a graph neural network to account for permutation equivariance, while a recurrent neural network encodes past trajectories. We further propose a conditional two-stream attention mechanism, to allow for efficient training of random factorizations. We experiment on trajectory data from professional soccer matches and find that we model low frequency trajectories better than variational approaches.",
keywords = "Informatics, Business informatics",
author = "Yannick Rudolph and Ulf Brefeld",
note = "Funding Information: We would like to thank Marius Lehne at SAP SE for his essential support and help while writing this paper as well as all reviewers for their valuable feedback. Publisher Copyright: Copyright {\textcopyright} 2022 by the author(s); The 25th International Conference on Artificial Intelligence and Statistics - AISTATS 2022, AISTATS 2022 ; Conference date: 28-03-2022 Through 30-03-2022",
year = "2022",
language = "English",
volume = "151",
pages = "10518--10533",
journal = "Proceedings of Machine Learning Research",
issn = "2640-3498",
publisher = "MLResearch Press",
url = "http://aistats.org/aistats2022/",

}

RIS

TY - JOUR

T1 - Modeling Conditional Dependencies in Multiagent Trajectories

AU - Rudolph, Yannick

AU - Brefeld, Ulf

N1 - Conference code: 25

PY - 2022

Y1 - 2022

N2 - We study modeling joint densities over sets of random variables (next-step movements of multiple agents) which are conditioned on aligned observations (past trajectories). For this setting, we propose an autoregressive approach to model intra-timestep dependencies, where distributions over joint movements are represented by autoregressive factorizations. In our approach, factors are randomly ordered and estimated with a graph neural network to account for permutation equivariance, while a recurrent neural network encodes past trajectories. We further propose a conditional two-stream attention mechanism, to allow for efficient training of random factorizations. We experiment on trajectory data from professional soccer matches and find that we model low frequency trajectories better than variational approaches.

AB - We study modeling joint densities over sets of random variables (next-step movements of multiple agents) which are conditioned on aligned observations (past trajectories). For this setting, we propose an autoregressive approach to model intra-timestep dependencies, where distributions over joint movements are represented by autoregressive factorizations. In our approach, factors are randomly ordered and estimated with a graph neural network to account for permutation equivariance, while a recurrent neural network encodes past trajectories. We further propose a conditional two-stream attention mechanism, to allow for efficient training of random factorizations. We experiment on trajectory data from professional soccer matches and find that we model low frequency trajectories better than variational approaches.

KW - Informatics

KW - Business informatics

UR - http://www.scopus.com/inward/record.url?scp=85163100847&partnerID=8YFLogxK

M3 - Conference article in journal

VL - 151

SP - 10518

EP - 10533

JO - Proceedings of Machine Learning Research

JF - Proceedings of Machine Learning Research

SN - 2640-3498

T2 - The 25th International Conference on Artificial Intelligence and Statistics - AISTATS 2022

Y2 - 28 March 2022 through 30 March 2022

ER -

Recently viewed

Activities

  1. Users’ Handedness and Performance when Controlling Integrated Input Devices - Implications for Automotive HMI
  2. The role of different forms of cohesion and readers' expectations towards different types of text
  3. Trajectory-based Lagrangian approaches for the extraction and characterization of coherent structures in turbulent convection
  4. Plasma shock wave simulation for laser shock processing
  5. Workshop Medzin I
  6. From Magic to Systemics. Heinz von Foerster and the Reenchantment of Science
  7. Travelling Codes
  8. Eine Podiumsdiskussion zu Fracking
  9. Robotic Mobile Fulfillment Systems
  10. Time and Organizational Development
  11. The global classroom: Introduction, presentation and workshops
  12. It's how, not what we use that matters - Communications Modes in the Internet
  13. Keeping drivers engaged in automated driving through maneuver control- effects on perceived control and responsibility
  14. "Information-Oriented Communicative Acting in the Internet: Communication Modes between Mass- and Interpersonal Communication"
  15. Plenary lecture eintitled: "Mathematical insights for advanced ice-clamping control in the context of Industry 4.0"
  16. Adaptive Modeling
  17. Changing learning environments at university? Comparing the learning strategies of non-traditional European students engaged in lifelong learning.
  18. Activating an Integrative Mindset Improves the Subjective Outcomes of Value-Driven Conflicts
  19. Towards a Techno-Ecology of Participation - 2017
  20. Teams are changing! Going into the wild to expand theory on dynamics in modern teamwork settings
  21. Where To Start? Exploring 1-Year-Students’ Preconceptions of Sustainable Development
  22. Knowledge Spaces
  23. Lena Meyer-Bergner’s conception of modernism between graphics and weaving, between folk art and technology

Publications

  1. Understanding the properties of isospectral points and pairs in graphs
  2. Knowledge-Enhanced Language Models Are Not Bias-Proof
  3. THE PARALLAX OF INDIVIDUATION
  4. From entity to process
  5. Control versus Complexity
  6. Predicting the Individual Mood Level based on Diary Data
  7. Machine Learning and Knowledge Discovery in Databases
  8. Improvements in Flexibility depend on Stretching Duration
  9. Machine Learning and Knowledge Discovery in Databases
  10. Efficacy of a Web-Based Intervention With Mobile Phone Support in Treating Depressive Symptoms in Adults With Type 1 and Type 2 Diabetes
  11. Speed of processing and stimulus complexity in low-frequency and high-frequency channels
  12. Serendipity as a Mechanism of Change and its Potential for Explaining Change Processes
  13. Determination of 10 particle-associated multiclass polar and semi-polar pesticides from small streams using accelerated solvent extraction
  14. Biodiversity in space and time - towards a grid mapping for Mongolia
  15. A Lyapunov Approach to Set the Parameters of a PI-Controller to Minimise Velocity Oscillations in a Permanent Magnet Synchronous Motor Using Chopper Control for Electrical Vehicles
  16. A Genetic Algorithm for the Dynamic Management of Cellular Reconfigurable Manufacturing Systems
  17. How to attract visitors with strategic, value-based experience design
  18. Semi-Supervised Generative Models for Multi-Agent Trajectories
  19. Binary Random Nets II
  20. A Process Perspective on Organizational Failure
  21. Developing robust field survey protocols in landscape ecology
  22. MICSIM: Concept, Developments, and Applications of a PC Microsimulation Model for Research and Teaching
  23. CHANGING RECREATIONAL ACTIVITIES FOR REDUCING INSOMNIA SEVERITY? RESULTS FROM A SERIAL MEDIATION ANALYSIS ON THE IMPACT OF RECREATIONAL BEHAVIOR AS A MECHANISM OF CHANGE IN DIGITAL INTERVENTIONS FOR INSOMNIA