EUVIMEDEUVIMED entdecken
Crossref

Directed Acyclic Graph Convolutional Networks

Samuel Rey, Hamed Ajorlou, Gonzalo Mateos

IEEE Transactions on Signal Processing · 2026 · 74 · 1847-1862

DOI: 10.1109/tsp.2026.3687632 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Signal Processing, 2026. Verfasst von Samuel Rey und 2 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Gefördert von: NSF, Spanish AEI, Comunidad de Madrid.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and the automated design of neural architectures. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural network (GNN) architecture designed specifically for convolutional learning from signals supported on DAGs. The DCN leverages causal graph filters to learn nodal representations that account for the partial ordering inherent to DAGs, a strong inductive bias not present in conventional GNNs. Unlike prior art in machine learning over DAGs, DCN builds on formal convolutional operations that admit spectral-domain representations. We further propose the Parallel DCN (PDCN), a model that feeds input DAG signals to a parallel bank of causal graph-shift operators and processes these DAG-aware features using a shared multilayer perceptron. This way, PDCN decouples model complexity from graph size while maintaining satisfactory predictive performance. The architectures’ permutation equivariance and expressive power properties are also established. Comprehensive numerical tests across several tasks, datasets, and experimental conditions demonstrate that (P)DCN compares favorably with state-of-the-art baselines in terms of accuracy, robustness, and computational efficiency. These results position (P)DCN as a viable framework for deep learning from DAG-structured data that is designed from first (graph) signal processing principles.

Förderung

  • NSF
  • Spanish AEI
  • Comunidad de Madrid
  • Madrid ELLIS Unit

Zitieren

APA

Rey, S., Ajorlou, H., & Mateos, G. (2026). Directed Acyclic Graph Convolutional Networks. IEEE Transactions on Signal Processing, 74, 1847-1862. https://doi.org/10.1109/tsp.2026.3687632

Vancouver

Rey S, Ajorlou H, Mateos G. Directed Acyclic Graph Convolutional Networks. IEEE Transactions on Signal Processing. 2026;74:1847-1862. doi:10.1109/tsp.2026.3687632

BibTeX
@article{Rey2026,
  author = {Rey, Samuel and Ajorlou, Hamed and Mateos, Gonzalo},
  title = {Directed Acyclic Graph Convolutional Networks},
  journal = {IEEE Transactions on Signal Processing},
  year = {2026},
  volume = {74},
  pages = {1847--1862},
  doi = {10.1109/tsp.2026.3687632}
}
Kostenlos starten →