mlsanityData to 14 Oct 2026

Federated Learning While Providing Model as a Service: Joint Training and Inference Optimization

arXiv 2312.12863 ↗First posted 20 Dec 2023cs.DC cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

While providing machine learning model as a service to process users' inference requests, online applications can periodically upgrade the model utilizing newly collected data. Federated learning (FL) is beneficial for enabling the training of models across distributed clients while keeping the data locally. However, existing work has overlooked the coexistence of model training and inference under clients' limited resources. This paper focuses on the joint optimization of model training and inference to maximize inference performance at clients. Such an optimization faces several challenges. The first challenge is to characterize the clients' inference performance when clients may partially participate in FL. To resolve this challenge, we introduce a new notion of age of model (AoM) to quantify client-side model freshness, based on which we use FL's global model convergence error as an approximate measure of inference performance. The second challenge is the tight coupling among clients' decisions, including participation probability in FL, model download probability, and service rates. Toward the challenges, we propose an online problem approximation to reduce the problem complexity and optimize the resources to balance the needs of model training and inference. Experimental results demonstrate that the proposed algorithm improves the average inference accuracy by up to 12%.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 28 of its 49 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

28 of 49 references.

References · 28

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  5. 2020Adaptive Federated Optimizationcited by 1,046
  6. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  7. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  8. 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 356
  9. 2018Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learningcited by 278
  10. 2018The Convergence of Sparsified Gradient Methodscited by 229
  11. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
  12. 2021Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learningcited by 93
16 more
  1. 2021MARINA: Faster Non-Convex Distributed Learning with Compressioncited by 78
  2. 2023FedExP: Speeding Up Federated Averaging via Extrapolationcited by 69
  3. 2021Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devicescited by 56
  4. 2019Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networkscited by 39
  5. 2020Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networkscited by 29
  6. 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
  7. 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
  8. 2018Scheduling Policies for Minimizing Age of Information in Broadcast Wireless Networkscited by 22
  9. 2022FedLite: A Scalable Approach for Federated Learning on Resource-constrained Clientscited by 15
  10. 2022Communication-Efficient Federated Learning for Heterogeneous Edge Devices Based on Adaptive Gradient Quantizationcited by 14
  11. 2022Federated Learning with Flexible Controlcited by 12
  12. 2022Adaptive Configuration for Heterogeneous Participants in Decentralized Federated Learningcited by 11
  13. 2023AnycostFL: Efficient On-Demand Federated Learning over Heterogeneous Edge Devicescited by 10
  14. 2021The Age of Correlated Features in Supervised Learning based Forecastingcited by 5
  15. 2023Joint Participation Incentive and Network Pricing Design for Federated Learningcited by 4
  16. 2023Network Adaptive Federated Learning: Congestion and Lossy Compressioncited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2024Hierarchical Split Federated Learning: Convergence Analysis and System Optimizationcited by 38
  2. 2025PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimizationcited by 32
  3. 2025APFL: Analytic Personalized Federated Learning via Dual-Stream Least Squarescited by 2
  4. 2025Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insightscited by 1
  5. 2026Graph Representation Learning Augmented Model Manipulation on Federated Fine-Tuning of LLMscited by 1
  6. 2025FedHiP: Heterogeneity-Invariant Personalized Federated Learning Through Closed-Form Solutionscited by 0
  7. 2026Joint Optimization of Training and Inference in Federated Edge Learning via Constrained Multi-Objective Deep Reinforcement Learningcited by 0
  8. 2026DART-FL: Burst-Aware Multitask Federated Learning under Dynamic Inference Demand at the Edgecited by 0