# Decentralized Federated Learning for Heterogeneous Multi-Task Semantic Communication

arXiv: https://arxiv.org/abs/2608.15256 · HTML: https://mlsanity.com/paper/2608.15256/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 15 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [Taskonomy: Disentangling Task Transfer Learning](https://mlsanity.com/paper/1804.08328/) (2018)
- [Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Condition](https://mlsanity.com/paper/1608.04636/) (2016)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Which Tasks Should Be Learned Together in Multi-task Learning?](https://mlsanity.com/paper/1905.07553/) (2019)
- [Personalized Cross-Silo Federated Learning on Non-IID Data](https://mlsanity.com/paper/2007.03797/) (2020)
- [Loss landscapes and optimization in over-parameterized non-linear systems and neural networks](https://mlsanity.com/paper/2003.00307/) (2020)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning](https://mlsanity.com/paper/1911.12423/) (2019)
- [NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction](https://mlsanity.com/paper/1801.08297/) (2018)
- [Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks](https://mlsanity.com/paper/1912.13163/) (2019)
- [Wireless Deep Video Semantic Transmission](https://mlsanity.com/paper/2205.13129/) (2022)
- [A Unified Multi-Task Semantic Communication System for Multimodal Data](https://mlsanity.com/paper/2209.07689/) (2022)
- [On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data](https://mlsanity.com/paper/2206.04723/) (2022)
- [FedHCA2: Towards Hetero-Client Federated Multi-Task Learning](https://mlsanity.com/paper/2311.13250/) (2023)
- [FedBone: Towards Large-Scale Federated Multi-Task Learning](https://mlsanity.com/paper/2306.17465/) (2023)
- [Scalable Multi-task Semantic Communication System with Feature Importance Ranking](https://mlsanity.com/paper/2304.05882/) (2023)
- [Decentralized Federated Learning Over Imperfect Communication Channels](https://mlsanity.com/paper/2405.12894/) (2024)
- [Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction](https://mlsanity.com/paper/2501.02006/) (2025)
- [SemSpaceFL: A Collaborative Hierarchical Federated Learning Framework for Semantic Communication in 6G LEO Satellites](https://mlsanity.com/paper/2505.00966/) (2025)
- [Route-and-Aggregate Decentralized Federated Learning Under Communication Errors](https://mlsanity.com/paper/2503.22186/) (2025)
- [Spectral-Convergent Decentralized Machine Learning: Theory and Application in Space Networks](https://mlsanity.com/paper/2511.03291/) (2025)
- [Enhancing Convergence, Privacy and Fairness for Wireless Personalized Federated Learning: Quantization-Assisted Min-Max Fair Scheduling](https://mlsanity.com/paper/2506.02422/) (2025)
- [Divergence-Based Adaptive Aggregation for Byzantine Robust Federated Learning](https://mlsanity.com/paper/2601.06903/) (2026)
- [Adaptive Dual-Path Framework for Covert Semantic Communication](https://mlsanity.com/paper/2605.03423/) (2026)

## Abstract (arXiv)

Collaborative training in distributed semantic communication (DSC) networks typically relies on decentralized federated learning (DFL). However, pushing topology-agnostic aggregation into heterogeneous, multi-task environments creates a fundamental bottleneck: it drives negative transfer and overconsensus bias (OCB). This paper introduces a personalized DSC framework that cuts off this cross-task interference. At the node level, a policy-driven multi-path routing mechanism separates task-specific features from shared representations to preserve local fidelity. Across the network, we deploy a "communicationwhile- aggregation" protocol. It calibrates a column-stochastic consensus matrix using task affinities. This limits the system to absorbing complementary knowledge while actively blocking mismatched parameter updates. To bound the convergence, we derive a unified Lyapunov drift analysis. We reveal a strict Ushaped trade-off: deeper topological mixing reduces variance but amplifies structural OCB. Resolving this tension yields a closed-form expression for the optimal aggregation depth. We evaluate the proposed framework on NYU-v2, where the results reveal a clear trade-off between insufficient aggregation and excessive topological mixing. At the analytically derived optimal aggregation depth, our method achieves a 4.77% global relative improvement over the no-aggregation baseline and outperforms decentralized FedAvg, FedAMP, and heuristic max aggregation. We further evaluate the framework on Taskonomy and imperfect wireless links to examine the effects of network-size variation and wireless-link reliability.