arXiv subjects

Jinhao Yi

Publications and source records attributed to Jinhao Yi.

3 recordsLinked to original sources

arXiv2026

L-COIN: LLM-Assisted Counterfactual Inference for Game-Theoretic Distributed Computation Offloading in Sub-THz LEO Satellite Networks

As Space-Based Information Networks (SBINs) evolve toward high-capacity, intelligence-centric paradigms, integrating sub-Terahertz (sub-THz) communication into Low Earth Orbit (LEO) satellite constellations has emerged as a critical enabler for ultra-broadband and resilient global connectivity. By exploiting the ultra-wide bandwidth of sub-THz links to reduce transmission delays, resource-constrained ground devices can seamlessly offload compute-intensive tasks to LEO edge servers. However, satellite motion, short visibility windows, and limited onboard resources make offloading decisions highly time-varying. Existing distributed offloading schemes typically require repeated inter-device state exchange and poorly adapt to time-varying LEO topology or traffic conditions. To address these limitations, a decentralized game-theoretic offloading framework empowered by large language models (LLMs) and counterfactual inference is proposed in this paper. First, a realistic offloading system is established by integrating time-varying 3D-Walker topology. Second, a game-theoretic scheme using counterfactual inference is introduced to deduce unobserved states from local histories, eliminating global information reliance. Finally, an LLM-empowered semantic fusion algorithm is integrated into the counterfactual inference to enhance adaptability through zero-shot reasoning and self-reflection. Numerical results show that L-COIN reduces offloading cost by 10.9% to 27.7% relative to state-of-the-art baselines.

eess.SY↗

arXiv2026

Topology-Aware Two-Stage Federated Learning via Proxy Models for Sub-THz Heterogeneous LEO Communications

Federated learning (FL) has emerged as a promising distributed training paradigm for Low Earth Orbit (LEO) networks by significantly reducing communication overhead. However, its deployment faces critical challenges, e.g., topology-induced model staleness, short contact windows, and unaddressed computing heterogeneity. To address these issues, a topology-aware two-stage FL framework is proposed in this paper. First, a multi-layer physical architecture utilizing high-altitude platforms (HAPs) and Sub-THz communications is designed to extend satellite-ground contact windows and enlarge available bandwidth. Second, a proxy-model-based approach is adopted to fully utilize heterogeneous resources and enable architecture-agnostic knowledge aggregation. Finally, building upon these foundations, a topology-aware two-stage aggregation mechanism is proposed as the central algorithmic design to overcome the topology-induced staleness. The mechanism dynamically partitions LEO satellites into localized groups based on their transient HAP coverage. Within each group, LEO satellites perform asynchronous aggregation at their associated HAP to naturally tolerate computational delays without penalizing faster nodes. Subsequently, a synchronous inter-group aggregation is executed among all HAPs at the Ground Station (GS) to strictly bound the maximum staleness and guarantee stable global convergence. Numerical results demonstrate the proposed framework extends contact windows and achieves 86.59%--90.57% test accuracy, outperforming the state-of-the-art heterogeneous baseline by 16.26\%--19.80\%. Furthermore, it achieves a 1.5x to 2.2x convergence speedup, which closely approaches the ideal upper bound.

eess.SP↗

arXiv2025

Diffusion-Driven Terahertz Air-Ground Communications under Dynamic Atmospheric Turbulence

The ever-increasing demand for ultra-high data rates in space-air-ground integrated networks (SAGINs) has rendered terahertz THz communications a promising technology owing to its exceptionally broad and continuous spectrum resources. Nevertheless, in air-ground (AG) scenarios, the high mobility of aircraft induces intense and rapidly fluctuating turbulence, leading to additional propagation loss that is often overlooked in existing studies. To bridge this gap, this paper presents an AI-empowered THz AG communication framework that explicitly models turbulence-induced attenuation through fluid dynamics and integrates it into an adaptive optimization paradigm for communication performance enhancement. Specifically, a fluid-dynamics-informed attenuation model is established to characterize aircraft-generated turbulence and quantify its impact on THz signal propagation. Building upon this model, a joint power-attitude optimization problem is formulated to adaptively allocate transmit power and adjust aircraft attitude for maximizing link capacity. The optimization problem is efficiently solved using a diffusion-based algorithm that learns the nonlinear relationship between flight configuration and turbulence-induced attenuation. Comprehensive numerical evaluations demonstrate that the turbulence-induced attenuation ranges from 18 to 28 dB under attacking angles between -10 degree and 10 degree at 0.7 Mach, verifying the pronounced impact of aircraft-induced turbulence on THz propagation. Furthermore, the proposed framework attains an average capacity of 11.241 bps/Hz, substantially outperforming existing strategies by 22.8% and 66.5%, and approaching approximately 98% of the theoretical capacity limit.

eess.SP↗