Masked graph autoencoder-based multi-agent dynamic relational inference model for trajectory prediction

Dynamic relational inference models uncover potential complex system interactions, enabling trajectory prediction and improving the interpretability of underlying system dynamics. However, the existing models cannot accurately infer the structural evolution trends and complete dynamic processes of t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neurocomputing (Amsterdam) Jg. 634; S. 129922
Hauptverfasser: Zhao, Fuyuan, Cao, Xiangang, Zhao, Jiangbin, Duan, Yong, Yang, Xin, Zhang, Xinyuan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 14.06.2025
Schlagworte:
Dynamic relational inference
Graph attention network
Masked graph autoencoder
Multi-agent
Trajectory prediction
Multi-agent
Masked graph autoencoder
Trajectory prediction
Dynamic relational inference
Graph attention network
ISSN:0925-2312
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Dynamic relational inference models uncover potential complex system interactions, enabling trajectory prediction and improving the interpretability of underlying system dynamics. However, the existing models cannot accurately infer the structural evolution trends and complete dynamic processes of temporal networks. Additionally, when uncertain noisy data are input, more serious graph noise problems, including redundant and noisy edges, occur, undermining the stability of interaction inference and reducing the accuracy of trajectory prediction. Therefore, a masked graph autoencoder-based multi-agent dynamic relational inference (MGAE-MDRI) trajectory prediction model is proposed herein. The mask reconstruction module is integrated into MDRI, where the partial edges of the interaction graph, representing multi-agent dynamic evolution, are masked through sampling. The reconstruction strategy leverages path and degree considerations to mitigate the impact of graph noise on the network topology. Furthermore, a graph attention network-based path sampler with a preference random walk is introduced, effectively combining network topology and node attribute features to construct a topologically weighted degree matrix and assign optimal mask sampling weights to neighboring nodes. Experiments conducted on four standard public datasets demonstrate that MGAE-MDRI outperforms the state-of-the-art models, achieving better trajectory prediction robustness and for complex multi-agent systems.
ISSN:0925-2312
DOI:10.1016/j.neucom.2025.129922