Omni-Flex GraphFormer: Parallel Fusion of Local Graph Aggregation and Global Attention Across Image Resolutions
Information · 02.11.2026 · 17 (11) · 1092
DOI: 10.3390/info17111092 ↗Kurz gefasst
Fachartikel in der Zeitschrift Information, online erschienen am 02.11.2026. Verfasst von Wiam Charchaoui und 4 weiteren Autor:innen. Die Arbeit nennt 83 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Center for Scientific and Technical Research.
Abstract (Originalsprache)
Graph neural networks (GNNs) capture local image structure with few parameters, whereas Vision Transformers (ViTs) model global context at a higher computational cost. We propose the Omni-Flex GraphFormer, which applies a graph branch (OMNIVIG: max-relative aggregation over a fixed 3×3 pixel neighbourhood) and a Transformer branch (FLEXIVIT: global multi-head self-attention) in parallel and sums their outputs. Because each baseline is the hybrid with one branch removed, comparing the three models on eight datasets from 8×8 to 96×96 pixels, under equal training budgets and over three seeds, is a controlled branch ablation. Global attention is decisive: the hybrid exceeds OMNIVIG in test macro-F1 on every dataset and in all 24 runs, by 3.7 to 15.1 points (Wilcoxon test, p=0.0078). Against FLEXIVIT, the hybrid has the best mean F1 on six datasets and a 40–62% smaller seed-to-seed spread on CIFAR-10 and CIFAR-100, but the difference is not significant (p=0.38). The graph branch adds only 0.5–3.1% to the number of multiply–accumulate operations, and under warmed-up timing, both models run at the same speed, whereas unwarmed timing overstates latency by up to 15×. Under Gaussian noise, the summed hybrid degrades like the graph branch, which motivates gated or attention-guiding fusion.
Förderung
- National Center for Scientific and Technical Research
Zitieren
APA
Charchaoui, W., Barrouch, M., Ouhmid, A., Barhdadi, M., & Moutaouakil, K. E. (2026). Omni-Flex GraphFormer: Parallel Fusion of Local Graph Aggregation and Global Attention Across Image Resolutions. Information, 17(11), 1092. https://doi.org/10.3390/info17111092
Vancouver
Charchaoui W, Barrouch M, Ouhmid A, Barhdadi M, Moutaouakil KE. Omni-Flex GraphFormer: Parallel Fusion of Local Graph Aggregation and Global Attention Across Image Resolutions. Information. 2026;17(11):1092. doi:10.3390/info17111092
BibTeX
@article{Charchaoui2026,
author = {Charchaoui, Wiam and Barrouch, Mohammed and Ouhmid, Azedine and Barhdadi, Mohamed and Moutaouakil, Karim El},
title = {Omni-Flex GraphFormer: Parallel Fusion of Local Graph Aggregation and Global Attention Across Image Resolutions},
journal = {Information},
year = {2026},
volume = {17},
number = {11},
pages = {1092},
doi = {10.3390/info17111092}
}
EUVIMED