Graph Conditional Variational Models: Too Complex for Multiagent Trajectories?

Publikation: Beiträge in ZeitschriftenKonferenzaufsätze in FachzeitschriftenForschungbegutachtet

Authors

Recent advances in modeling multiagent trajectories combine graph architectures such as graph neural networks (GNNs) with conditional variational models (CVMs) such as variational RNNs (VRNNs). Originally, CVMs have been proposed to facilitate learning with multi-modal and structured data and thus seem to perfectly match the requirements of multi-modal multiagent trajectories with their structured output spaces. Empirical results of VRNNs on trajectory data support this assumption. In this paper, we revisit experiments and proposed architectures with additional rigour, ablation runs and baselines. In contrast to common belief, we show that prior results with CVMs on trajectory data might be misleading. Given a neural network with a graph architecture and/or structured output function, variational autoencoding does not seem to contribute statistically significantly to empirical performance. Instead, we show that well-known emission functions do contribute, while coming with less complexity, engineering and computation time.
OriginalspracheEnglisch
ZeitschriftProceedings of Machine Learning Research
Jahrgang137
Seiten (von - bis)136-147
Anzahl der Seiten12
ISSN2640-3498
PublikationsstatusErschienen - 2020
VeranstaltungVirtual NeurIPS 2020: Neural Information Processing Systems Online Conference 2020 - digital
Dauer: 06.12.202012.12.2020
Konferenznummer: 34
https://neurips.cc/virtual/2020/public/index.html
https://proceedings.mlr.press/v137/

Bibliographische Notiz

Publisher Copyright:
© Proceedings of Machine Learning Research 2020.

Zugehörige Aktivitäten

Links

Zuletzt angesehen

Publikationen

  1. Random measurement and prediction errors limit the practical relevance of two velocity sensors to estimate the 1RM back squat
  2. Towards a Dynamic Interpretation of Subjective and Objective Values
  3. Substructure, subgraph, and walk counts as measures of the complexity of graphs and molecules.
  4. Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System
  5. Building Assistance Systems using Distributed Knowledge Representations
  6. DialogueMaps: Supporting interactive transdisciplinary dialogues with a web-based tool for multi-layer knowledge maps
  7. The learning net - an interactive representation of shared knowledge
  8. Set-oriented numerical computation of rotation sets
  9. Isocodal and isospectral points, edges, and pairs in graphs and how to cope with them in computerized symmetry recognition
  10. Making an Impression Through Openness
  11. A model predictive control for an aggregate actuator with a self-tuning initial condition procedure in combustion engines
  12. A discrete approximate solution for the asymptotic tracking problem in affine nonlinear systems
  13. Multi-Parallel Sending Coils for Movable Receivers in Inductive Charging Systems
  14. Control of a Sun Tracking Robot Based on Adaptive Sliding Mode Control with Kalman Filtering and Model Predictive Control
  15. Anomaly detection in formed sheet metals using convolutional autoencoders
  16. Framework for setting up and operating biobanks
  17. Perfect anti-windup in output tracking scheme with preaction
  18. Introducing a multivariate model for predicting driving performance
  19. Semantic Parsing for Knowledge Graph Question Answering with Large Language Models
  20. Reading and Calculating in Word Problem Solving
  21. Selection and Recognition of Statistically Defined Signals in Learning Systems
  22. Inversion of fuzzy neural networks for the reduction of noise in the control loop
  23. Age-related differences in processing visual device and task characteristics when using technical devices
  24. Evaluating the construct validity of Objective Personality Tests using a multitrait-multimethod-Multioccasion-(MTMM-MO)-approach
  25. A denoising procedure using wavelet packets for instantaneous detection of pantograph oscillations
  26. Managing Business Process in Distributed Systems: Requirements, Models, and Implementation
  27. Evaluating OWL 2 reasoners in the context of checking entity-relationship diagrams during software development
  28. The elicitation process in developing of case library for Case-Based Reasoner system whilst consideration for validating electronic communication technologies
  29. A multi input sliding mode control for Peltier Cells using a cold-hot sliding surface
  30. Design and Control of an Inductive Power Transmission System with AC-AC Converter for a Constant Output Current
  31. On robustness properties in permanent magnet machine control by using decoupling controller
  32. Construct Objectification and De-Objectification in Organization Theory
  33. Vision-Based Deep Learning Algorithm for Detecting Potholes
  34. Methodologies for Noise and Gross Error Detection using Univariate Signal-Based Approaches in Industrial Application
  35. A model predictive control in Robotino and its implementation using ROS system