实时推断动态多智能体交互关系，支持在线学习与自适应更新。
Online Relational Inference for Evolving Multi-agent Interacting Systems
- 基于在线反向传播，每来新数据就更新模型，实现环境自适应。
- 使用可训练邻接矩阵，结合自适应学习率AdaRelation，提升推理精度。
- 适用于复杂动态系统，如人体运动分析，可集成多种神经推理模型。
我们提出一种新型框架Online Relational Inference (ORI)，用于在流式数据下高效识别演化中的多智能体系统的隐藏交互图。与依赖固定训练集的传统离线方法不同，ORI采用在线反向传播，随每个新数据点实时更新模型，从而适应动态环境。核心创新在于将邻接矩阵设为可训练参数，并通过名为AdaRelation的自适应学习率技术进行优化，该技术根据解码器对交互图变化的历史敏感度动态调整。此外，引入轨迹镜像（Trajectory Mirror, TM）数据增强方法，通过暴露于多样化的轨迹模式提升模型泛化能力。在合成数据集和真实世界数据（CMU MoCap人体运动数据）上的实验表明，相较于现有方法，ORI在动态场景中显著提升了关系推断的准确性和适应性。该方法具有模型无关性，可无缝集成至各类神经关系推断（NRI）架构中，为复杂演化系统提供可靠的实时解决方案。
原文摘要 · Abstract (English)
We introduce a novel framework, Online Relational Inference (ORI), designed to efficiently identify hidden interaction graphs in evolving multi-agent interacting systems using streaming data. Unlike traditional offline methods that rely on a fixed training set, ORI employs online backpropagation, updating the model with each new data point, thereby allowing it to adapt to changing environments in real-time. A key innovation is the use of an adjacency matrix as a trainable parameter, optimized through a new adaptive learning rate technique called AdaRelation, which adjusts based on the historical sensitivity of the decoder to changes in the interaction graph. Additionally, a data augmentation method named Trajectory Mirror (TM) is introduced to improve generalization by exposing the model to varied trajectory patterns. Experimental results on both synthetic datasets and real-world data (CMU MoCap for human motion) demonstrate that ORI significantly improves the accuracy and adaptability of relational inference in dynamic settings compared to existing methods. This approach is model-agnostic, enabling seamless integration with various neural relational inference (NRI) architectures, and offers a robust solution for real-time applications in complex, evolving systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。