# Resource Allocation in Hybrid Radio-Optical IoT Networks using GNN with Multi-task Learning

arXiv: https://arxiv.org/abs/2511.07428 · HTML: https://mlsanity.com/paper/2511.07428/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 64 references that are in the map.
- First posted on arXiv 29 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks](https://mlsanity.com/paper/1909.01865/) (2019)
- [Combining Induction and Transduction for Abstract Reasoning](https://mlsanity.com/paper/2411.02272/) (2024)
- [Graph Neural Networks for Wireless Communications: From Theory to Practice](https://mlsanity.com/paper/2203.10800/) (2022)
- [Towards Understanding the Generalization of Graph Neural Networks](https://mlsanity.com/paper/2305.08048/) (2023)
- [Structured Consistency Loss for semi-supervised semantic segmentation](https://mlsanity.com/paper/2001.04647/) (2020)
- [Distributed Scheduling using Graph Neural Networks](https://mlsanity.com/paper/2011.09430/) (2020)
- [Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities](https://mlsanity.com/paper/2112.14792/) (2021)
- [Low Complexity Recruitment for Collaborative Mobile Crowdsourcing Using Graph Neural Networks](https://mlsanity.com/paper/2106.00717/) (2021)
- [Temporal Encoding Strategies for Energy Time Series Prediction](https://mlsanity.com/paper/2503.15456/) (2025)
- [Minimizing the AoI in Resource-Constrained Multi-Source Relaying Systems: Dynamic and Learning-based Scheduling](https://mlsanity.com/paper/2203.05656/) (2022)
- [Service Discovery in Social Internet of Things using Graph Neural Networks](https://mlsanity.com/paper/2205.12711/) (2022)
- [Age of Information Optimization in Multi-Channel Network with Sided Information](https://mlsanity.com/paper/2212.07114/) (2022)
- [Optimal Design of Energy-Harvesting Hybrid VLC-RF Networks](https://mlsanity.com/paper/2206.04635/) (2022)
- [AoI in Context-Aware Hybrid Radio-Optical IoT Networks](https://mlsanity.com/paper/2412.12914/) (2024)

## Abstract (arXiv)

This paper addresses the problem of dual-technology scheduling in hybrid Internet-of-Things (IoT) networks that integrate Optical Wireless Communication (OWC) with Radio Frequency (RF). We first present an optimization formulation that jointly maximizes throughput and minimizes delivery-based Age of Information (AoI) between access points and IoT nodes under energy and link availability constraints. However, solving such NP-hard problems at scale is computationally intractable and typically assumes full channel observability, which is impractical in real deployments. To address this challenge, we propose the Dual-Graph Embedding with Transformer (DGET) framework, a supervised multi-task learning architecture that combines a two-stage Graph Neural Network (GNN) with a Transformer encoder. The first stage employs a transductive GNN to encode the known graph topology together with initial node and link states, such as energy levels, available links, and queued transmissions. The second stage introduces an inductive GNN for temporal refinement, enabling the model to generalize these embeddings to evolving network states while capturing variations in energy and queue dynamics over time through a consistency loss. The resulting embeddings are then processed by a Transformer-based classifier that models cross-link dependencies using multi-head self-attention. Simulation results show that hybrid RF-OWC networks outperform standalone RF systems by supporting higher traffic loads and reducing AoI by up to 20% while maintaining comparable energy consumption. Compared with optimization-based methods, the proposed DGET framework achieves near-optimal scheduling with over 90% classification accuracy, lower computational complexity, and improved robustness under partial channel observability.