# Edge Learning via Federated Split Decision Transformers for Metaverse Resource Allocation

arXiv: https://arxiv.org/abs/2602.16174 · HTML: https://mlsanity.com/paper/2602.16174/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 18 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Split Learning in 6G Edge Networks](https://mlsanity.com/paper/2306.12194/) (2023)
- [Decision Transformers for Wireless Communications: A New Paradigm of Resource Management](https://mlsanity.com/paper/2404.05199/) (2024)
- [Attention-based QoE-aware Digital Twin Empowered Edge Computing for Immersive Virtual Reality](https://mlsanity.com/paper/2305.08569/) (2023)
- [Harnessing the Power of LLMs, Informers and Decision Transformers for Intent-driven RAN Management in 6G](https://mlsanity.com/paper/2505.01841/) (2025)
- [Learning-based Prediction, Rendering and Association Optimization for MEC-enabled Wireless Virtual Reality (VR) Network](https://mlsanity.com/paper/2005.08332/) (2020)
- [Upper Mid-Band Spectrum for 6G: Vision, Opportunity and Challenges](https://mlsanity.com/paper/2502.17914/) (2025)
- [FoVR: Attention-based VR Streaming through Bandwidth-limited Wireless Networks](https://mlsanity.com/paper/2209.15198/) (2022)
- [Personalized Federated Deep Reinforcement Learning for Heterogeneous Edge Content Caching Networks](https://mlsanity.com/paper/2412.12543/) (2024)
- [Distributed Attacks over Federated Reinforcement Learning-enabled Cell Sleep Control](https://mlsanity.com/paper/2311.15894/) (2023)
- [Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Training](https://mlsanity.com/paper/2405.13445/) (2024)

## Built on by (most cited first, 3 of 3)

- [Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision Transformers](https://mlsanity.com/paper/2606.04328/) (2026)
- [Multi-Agent Transformer for Queue-Level XR Traffic Scheduling in TSN Networks](https://mlsanity.com/paper/2608.05340/) (2026)
- [WiSDoM: Wireless Sparse Decision Transformer with Mixture-of-Experts for Multi-Task Mobile Network Optimization](https://mlsanity.com/paper/2609.00284/) (2026)

## Abstract (arXiv)

Mobile edge computing (MEC) based wireless metaverse services offer an untethered, immersive experience to users, where the superior quality of experience (QoE) needs to be achieved under stringent latency constraints and visual quality demands. To achieve this, MEC-based intelligent resource allocation for virtual reality users needs to be supported by coordination across MEC servers to harness distributed data. Federated learning (FL) is a promising solution, and can be combined with reinforcement learning (RL) to develop generalized policies across MEC-servers. However, conventional FL incurs transmitting the full model parameters across the MEC-servers and the cloud, and suffer performance degradation due to naive global aggregation, especially in heterogeneous multi-radio access technology environments. To address these challenges, this paper proposes Federated Split Decision Transformer (FSDT), an offline RL framework where the transformer model is partitioned between MEC servers and the cloud. Agent-specific components (e.g., MEC-based embedding and prediction layers) enable local adaptability, while shared global layers in the cloud facilitate cooperative training across MEC servers. Experimental results demonstrate that FSDT enhances QoE for up to 10% in heterogeneous environments compared to baselines, while offloadingnearly 98% of the transformer model parameters to the cloud, thereby reducing the computational burden on MEC servers.