Nash-regularized heterogeneous graph transformer networks for strategic task offloading in 6G edge computing
Bibliographic record
Abstract
The rapid urbanization and digital transformation of modern cities demand intelligent infrastructure capable of supporting massive IoT deployments and real-time decision-making across diverse smart city applications. The evolution toward sixth-generation (6G) wireless networks introduces unprecedented challenges for task offloading due to ultra-low latency, massive connectivity, and heterogeneous device requirements in urban environments. Traditional methods face limitations in scalability, adaptability, and multi-agent coordination needed for city-scale deployments. To address these gaps, we propose the Heterogeneous Graph Transformer Deep Q-Network with Nash Equilibrium Integration (HGT-DQN-NEI), a novel framework that synergistically combines graph neural networks, transformer architectures, reinforcement learning, and game-theoretic principles for intelligent multi-agent task offloading. The heterogeneous graph transformer effectively models complex 6G topologies, while the Deep Transformer Q-Network enhances decision making under partial observability. A distributed Nash equilibrium mechanism ensures stable coordination among agents with provable convergence guarantees. Extensive experiments validate the proposed approach across diverse scenarios, including urban, highway, industrial, and rural deployments. Results demonstrate a 23.4% reduction in task completion latency, 31.7% improvement in energy efficiency, and 18.9% enhancement in resource utilization compared to state-of-the-art baselines. The framework achieves stable convergence within approximately 30–50 episodes and scales efficiently to networks with over 1000 heterogeneous agents, while maintaining sub-millisecond decision times essential for smart city applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.004 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".