Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network

• URL: http://arxiv.org/abs/2107.00894v1
• Date: Fri, 2 Jul 2021 08:20:06 GMT
• Title: Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network
• Authors: Maosen Li, Siheng Chen, Yanning Shen, Genjia Liu, Ivor W. Tsang, Ya Zhang
• Abstract summary: We propose a novel collaborative prediction unit (CoPU), which aggregates predictions from multiple collaborative predictors according to a collaborative graph. Our methods outperform state-of-the-art works on the three tasks by 28.6%, 17.4% and 21.0% on average.
• Score: 65.11999700562869
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper considers predicting future statuses of multiple agents in an online fashion by exploiting dynamic interactions in the system. We propose a novel collaborative prediction unit (CoPU), which aggregates the predictions from multiple collaborative predictors according to a collaborative graph. Each collaborative predictor is trained to predict the status of an agent by considering the impact of another agent. The edge weights of the collaborative graph reflect the importance of each predictor. The collaborative graph is adjusted online by multiplicative update, which can be motivated by minimizing an explicit objective. With this objective, we also conduct regret analysis to indicate that, along with training, our CoPU achieves similar performance with the best individual collaborative predictor in hindsight. This theoretical interpretability distinguishes our method from many other graph networks. To progressively refine predictions, multiple CoPUs are stacked to form a collaborative graph neural network. Extensive experiments are conducted on three tasks: online simulated trajectory prediction, online human motion prediction and online traffic speed prediction, and our methods outperform state-of-the-art works on the three tasks by 28.6%, 17.4% and 21.0% on average, respectively.

Related papers

• Human Action Anticipation: A Survey [86.415721659234]
  The literature on behavior prediction spans various tasks, including action anticipation, activity forecasting, intent prediction, goal prediction, and so on. Our survey aims to tie together this fragmented literature, covering recent technical innovations as well as the development of new large-scale datasets for model training and evaluation.
  arXiv  Detail & Related papers  (2024-10-17T21:37:40Z)
• Temporal Link Prediction Using Graph Embedding Dynamics [0.0]
  Temporal link prediction in dynamic networks is of particular interest due to its potential for solving complex scientific and real-world problems. Traditional approaches to temporal link prediction have focused on finding the aggregation of dynamics of the network as a unified output. We propose a novel perspective on temporal link prediction by defining nodes as Newtonian objects and incorporating the concept of velocity to predict network dynamics.
  arXiv  Detail & Related papers  (2024-01-15T07:35:29Z)
• Best Practices for 2-Body Pose Forecasting [58.661899246497896]
  We review the progress in human pose forecasting and provide an in-depth assessment of the single-person practices that perform best. Other single-person practices do not transfer to 2-body, so the proposed best ones do not include hierarchical body modeling or attention-based interaction encoding. Our proposed 2-body pose forecasting best practices yield a performance improvement of 21.9% over the state-of-the-art on the most recent ExPI dataset.
  arXiv  Detail & Related papers  (2023-04-12T10:46:23Z)
• Conditional Goal-oriented Trajectory Prediction for Interacting Vehicles with Vectorized Representation [10.190939530193502]
  Conditional Goal-oriented Trajectory Prediction (CGTP) framework to jointly generate scene-compliant trajectories of two interacting agents. Three main stages: context encoding, goal interactive prediction and trajectory interactive prediction. New goal interactive loss is developed to better learn the joint probability distribution over goal candidates between two interacting agents.
  arXiv  Detail & Related papers  (2022-10-19T15:14:46Z)
• GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning [37.64048110462638]
  GroupNet is a multiscale hypergraph neural network that captures both pair-wise and group-wise interactions. We apply GroupNet into both CVAE-based prediction system and previous state-of-the-art prediction systems. We show that with GroupNet, the CVAE-based prediction system outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-19T09:36:20Z)
• Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction [33.51444435524345]
  Our method is based on the observation that a good initial guess of the future poses is very helpful in improving the forecasting accuracy. We propose a novel two-stage prediction framework, including an init-prediction network that just computes the good guess. We extend this idea further and design a multi-stage prediction framework where each stage predicts initial guess for the next stage.
  arXiv  Detail & Related papers  (2022-03-30T04:35:53Z)
• Test-time Collective Prediction [73.74982509510961]
  Multiple parties in machine learning want to jointly make predictions on future test points. Agents wish to benefit from the collective expertise of the full set of agents, but may not be willing to release their data or model parameters. We explore a decentralized mechanism to make collective predictions at test time, leveraging each agent's pre-trained model.
  arXiv  Detail & Related papers  (2021-06-22T18:29:58Z)
• Adversarial Refinement Network for Human Motion Prediction [61.50462663314644]
  Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend. We propose an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation.
  arXiv  Detail & Related papers  (2020-11-23T05:42:20Z)
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction [69.1473775184952]
  We introduce a realistic problem of few-shot out-of-graph link prediction. We tackle this problem with a novel transductive meta-learning framework. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
  arXiv  Detail & Related papers  (2020-06-11T17:42:46Z)
• PTP: Parallelized Tracking and Prediction with Graph Neural Networks and Diversity Sampling [34.68114553744956]
  Multi-object tracking (MOT) and trajectory prediction are two critical components in modern 3D perception systems. We propose a parallelized framework to learn a shared feature representation of agent interaction. Our method with socially-aware feature learning and diversity sampling achieves new state-of-the-art performance on 3D MOT and trajectory prediction.
  arXiv  Detail & Related papers  (2020-03-17T17:53:33Z)

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.