TGraphX: Tensor-Aware Graph Neural Network for Multi-Dimensional Feature Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sajjadi, Arash, Eramian, Mark
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917977517981696
author Sajjadi, Arash
Eramian, Mark
author_facet Sajjadi, Arash
Eramian, Mark
contents TGraphX presents a novel paradigm in deep learning by unifying convolutional neural networks (CNNs) with graph neural networks (GNNs) to enhance visual reasoning tasks. Traditional CNNs excel at extracting rich spatial features from images but lack the inherent capability to model inter-object relationships. Conversely, conventional GNNs typically rely on flattened node features, thereby discarding vital spatial details. TGraphX overcomes these limitations by employing CNNs to generate multi-dimensional node features (e.g., (3*128*128) tensors) that preserve local spatial semantics. These spatially aware nodes participate in a graph where message passing is performed using 1*1 convolutions, which fuse adjacent features while maintaining their structure. Furthermore, a deep CNN aggregator with residual connections is used to robustly refine the fused messages, ensuring stable gradient flow and end-to-end trainability. Our approach not only bridges the gap between spatial feature extraction and relational reasoning but also demonstrates significant improvements in object detection refinement and ensemble reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2504_03953
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TGraphX: Tensor-Aware Graph Neural Network for Multi-Dimensional Feature Learning
Sajjadi, Arash
Eramian, Mark
Computer Vision and Pattern Recognition
Artificial Intelligence
68T07, 68T45, 68R10
I.2.6; I.5.1; I.4.8
TGraphX presents a novel paradigm in deep learning by unifying convolutional neural networks (CNNs) with graph neural networks (GNNs) to enhance visual reasoning tasks. Traditional CNNs excel at extracting rich spatial features from images but lack the inherent capability to model inter-object relationships. Conversely, conventional GNNs typically rely on flattened node features, thereby discarding vital spatial details. TGraphX overcomes these limitations by employing CNNs to generate multi-dimensional node features (e.g., (3*128*128) tensors) that preserve local spatial semantics. These spatially aware nodes participate in a graph where message passing is performed using 1*1 convolutions, which fuse adjacent features while maintaining their structure. Furthermore, a deep CNN aggregator with residual connections is used to robustly refine the fused messages, ensuring stable gradient flow and end-to-end trainability. Our approach not only bridges the gap between spatial feature extraction and relational reasoning but also demonstrates significant improvements in object detection refinement and ensemble reasoning.
title TGraphX: Tensor-Aware Graph Neural Network for Multi-Dimensional Feature Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
68T07, 68T45, 68R10
I.2.6; I.5.1; I.4.8
url https://arxiv.org/abs/2504.03953