# Task-oriented Framework for Communication-Efficient Federated Learning: From Isolated Optimization to Holistic Synergy

arXiv: https://arxiv.org/abs/2609.04945 · HTML: https://mlsanity.com/paper/2609.04945/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 15 references that are in the map.
- First posted on arXiv 4 Sep 2026.

## Builds on (most cited first, 8 of 8)

- [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019)
- [FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2108.06098/) (2021)
- [TiFL: A Tier-based Federated Learning System](https://mlsanity.com/paper/2001.09249/) (2020)
- [Optimized Power Control Design for Over-the-Air Federated Edge Learning](https://mlsanity.com/paper/2106.09316/) (2021)
- [Advances and Open Challenges in Federated Foundation Models](https://mlsanity.com/paper/2404.15381/) (2024)
- [A Multi-agent Reinforcement Learning Approach for Efficient Client Selection in Federated Learning](https://mlsanity.com/paper/2201.02932/) (2022)
- [Greedy Shapley Client Selection for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2312.09108/) (2023)
- [Joint Communication and Over-the-Air Computation for Semi-Federated Learning Towards Scalable AI in Computing-Heterogeneous IoT Systems](https://mlsanity.com/paper/2405.17453/) (2024)

## Abstract (arXiv)

Communication bottlenecks remain a primary obstacle to the large-scale deployment of federated learning (FL). This article proposes a comprehensive framework for building communication-efficient FL, founded on three fundamental pillars: model compression, client selection, and resource allocation. We first survey state-of-the-art techniques for each pillar, specifically elucidating how quantization, pruning, and low-rank approximation reduce payloads; how intelligent client schedulers exploit heterogeneity; and how emerging communication paradigms such as Integrated Sensing and Communication (ISAC) and Over-the-Air Computation (AirComp) redefine bandwidth and energy utilization. Subsequently, these insights are unified through a task-oriented design philosophy that couples strategy selection with cross-layer, multi-objective optimization. To validate the proposed framework, we present an autonomous driving case study with two complementary experiments: a task-oriented client scheduling strategy that improves object detection accuracy under the same communication time budget, and a joint quantization-bandwidth optimization that further reduces total training time under dynamic networks. Together, the experiments demonstrate the advantages of holistic task-oriented design for real-world FL deployment.