Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM

This paper explores the challenges of implementing Federated Learning (FL) in practical scenarios featuring isolated nodes with data heterogeneity, which can only be connected to the server through wireless links in an infrastructure-less environment. To overcome these challenges, we propose a novel mobilizing personalized FL approach, which aims to facilitate mobility and resilience. Specifically, we develop a novel optimization algorithm called Random Walk Stochastic Alternating Direction Method of Multipliers (RWSADMM). RWSADMM capitalizes on the server's random movement toward clients and formulates local proximity among their adjacent clients based on hard inequality constraints rather than requiring consensus updates or introducing bias via regularization methods. To mitigate the computational burden on the clients, an efficient stochastic solver of the approximated optimization problem is designed in RWSADMM, which provably converges to the stationary point almost surely in expectation. Our theoretical and empirical results demonstrate the provable fast convergence and substantial accuracy improvements achieved by RWSADMM compared to baseline methods, along with its benefits of reduced communication costs and enhanced scalability.

Paper

Similar papers

Peer review

Reviewer cJVn4/10 · confidence 4/52023-07-06

Summary

Authors consider in this paper a Federated Learning framework with a mobile server. They propose an algorithm named Random Walk Stochastic Alternating Direction Method of Multipliers (RWSADMM) for networks with instability and limited capacity. To overcome the non-IID nature of clients' data, they ensure local proximity among adjacent clients using hard inequality constraints. Their theoretical and empirical results demonstrate the effectiveness of RWSADMM.

Strengths

The mobile Federated Learning in infrastructure-less environment is an important problem. The paper is well organized with rigorous theoretic analysis.

Weaknesses

The random walk mobility model is over simplified and is not a realistic model for wireless adhoc network. The random walk model was initially developed to emulate the unpredictable movement of particles in physics. It is a memoryless mobility model that does not consider temporal and spatial correlation. In addition, topology control technique is a must to ensure reliable operation of a wireless adhoc network in reality and therefore such a memoryless assumption is hardly the case in many real life applications. Although the concept of the Federated Learning (FL) framework with a mobile server is interesting, it seems to be a special case of asynchronous FL, where only a subset of clients is selected to participate in the update in each iteration. Authors are recommended to elaborate the difference between this work and existing asynchronous FL work in the literature.

Questions

Can authors elaborate more regarding employing the dynamic Markov Chain to model the server's movement? The introduction of the y-variable in Eq. (7) is unclear. If one of the neighboring nodes of the selected node in an iteration fails to respond, does the algorithm still work?

Rating

4: Borderline reject: Technically solid paper where reasons to reject, e.g., limited evaluation, outweigh reasons to accept, e.g., good evaluation. Please use sparingly.

Confidence

4: You are confident in your assessment, but not absolutely certain. It is unlikely, but not impossible, that you did not understand some parts of the submission or that you are unfamiliar with some pieces of related work.

Soundness

3 good

Presentation

2 fair

Contribution

2 fair

Limitations

The mobility model considered in this paper is of limited applicability.

Reviewer J9bJ7/10 · confidence 3/52023-07-06

Summary

This paper proposes random walk stochastic method based on traditional ADMM, which enables personalized federated learning considering the mobility of clients and using a mobilized server. The authors solve the optimization of the stored client’s model parameters through Lagrangian and dual problem. The theoretical analysis proves the convergence performance of the proposed algorithm based on assumptions 4.1 to 4.5. The paper validates the performance of the algorithm by comparing its accuracy and loss with APFL/Ditto/PerAvg/FedAvg/pFedMe.

Strengths

1.This paper realizes the mobilizing federated learning in a in an infrastructure-less environment for the first time. 2.This paper has rigorously proposed the RWSADMM algorithm and rigorously proves its convergence performance. 3.The paper solves the model update faster by solving the dual problem and achieves better communication cost.

Weaknesses

1.The paper assume the mobilized server wanders in the region following a random walk pattern, and uses the warzone as an example. In a drastic combat, the mobilized server should usually follow a more regularized route instead of randomly wandering in the field. Also, the client are also set to be stationary in the paper, which can not represent usual moving soldiers and devices. Therefore, I think the system model is not very realistic, and the applicability of the system in a real war may be limited.

Questions

1.On page 8, the authors claim RWSADMM’s O(\omega^{-1}) communication complexity is better than Per-FedAvg’s O(\omega^{-3/2}) complexity. This hold when \omega ranges from 0 to 1, but the authors seem not to discuss or define the range of the parameter.

Rating

7: Accept: Technically solid paper, with high impact on at least one sub-area, or moderate-to-high impact on more than one areas, with good-to-excellent evaluation, resources, reproducibility, and no unaddressed ethical considerations.

Confidence

3: You are fairly confident in your assessment. It is possible that you did not understand some parts of the submission or that you are unfamiliar with some pieces of related work. Math/other details were not carefully checked.

Soundness

3 good

Presentation

3 good

Contribution

3 good

Limitations

N/A

Reviewer 46UP6/10 · confidence 4/52023-07-06

Summary

This paper proposes a new FL setting that involves a dynamically moving server among clients residing in different regions and receiving updates from clients of the selected region through wireless links. The proposed algorithm RWSADMM addresses personalization and data heterogeneity by minimizing the local proximity among neighbor nodes of each client. Additionally, the authors apply a first-order subgradient expansion for computational complexity reduction, which is useful for real-world applications. The algorithm is demonstrated to converge provably faster than baseline methods through theoretical analysis and experimental comparisons.

Strengths

This paper introduces a novel asynchronous mobilizing federated learning setting that can be utilized in realistic war situations where communication infrastructure is unavailable. Additionally, it establishes a mathematical framework based on dynamic graph-based representation, allowing the server to move through the field and interact with various clients to update the neural network. The proposed algorithm surpasses the baseline methods by a significant margin, demonstrating notably faster convergence rates, particularly in realistic non-IID scenarios. The methodology employed in this study is a theoretically sound solution derived from the analysis of dynamic Markov Chain and Alternating Direction Method of Multipliers. The proposed RWSADMM algorithm ensures convergence based on commonly assumed properties of the loss function. Furthermore, the communication complexity of RWSADMM is compared to existing methods like Per-FedAvg and APFL, providing theoretical evidence of its superior scalability. In the proposed setting, both convex and non-convex models converge faster and exhibit higher accuracy performance compared to the baseline methods.

Weaknesses

The proposed setting (mobilized federated learning) seems somewhat unrealistic. In a war situation where long-range communication is not supported, is there a need for federated learning? Considering that neural networks are large and transmitting them via tactical vehicles would be challenging, wouldn't it be better to transmit data for distributed learning or perform centralized learning on the server, rather than transmitting model updates? The proposed Markov Chain does not seem to effectively represent the problem situation (mobilized federated learning). In real scenarios, nodes within the communication range of the communication vehicle should be selected, but the proposed algorithm does not consider the physical distances between nodes. Additionally, considering realistic situations like Figure 3, where nodes (walking soldiers) move and the topology keeps changing, the Markov Chain used in this paper cannot reflect spatial rearrangements of participating nodes. I am concerned about privacy issues. In the proposed algorithm, each node needs to receive model updates from neighboring nodes to calculate the proximity term. However, this process can expose the data that the node possesses, as it can be extracted from the updates of other nodes. Furthermore, simultaneous reception of model updates from multiple nodes can result in communication overhead. There is a lack of ablation study on the proposed components. There is no analysis on how well the proposed local proximity term resolves data heterogeneity, and no trade-off analysis on how much computational resources are saved through first-order expansion and the corresponding impact on performance.

Questions

In the current problem, the server moves through a random walk. However, in practical situations, shouldn't the server actively modify its routing to reach unseen nodes? Looking at the Experimental setup in Section 5, there are only 20 clients. Considering the trend in recently published Federated learning works, shouldn't the proposed algorithm be compatible with scenarios involving a larger number of clients? In Figure 2, although PerAvg and APFL are FL works geared to data heterogeneity, their performances are significantly lower compared to FedAvg. Why does this discrepancy occur? What are the confidence intervals for the reported performance in Figure 2 and Table 1? It is important to report confidence intervals, as performance can vary significantly depending on how the spatial relationship between nodes is initialized. The proposed setting (mobilized federated learning) seems somewhat unrealistic. In a war situation where long-range communication is not supported, is there a need for federated learning? Considering that neural networks are large and transmitting them via tactical vehicles would be challenging, wouldn't it be better to transmit data for distributed learning or perform centralized learning on the server, rather than transmitting model updates?

Rating

6: Weak Accept: Technically solid, moderate-to-high impact paper, with no major concerns with respect to evaluation, resources, reproducibility, ethical considerations.

Confidence

4: You are confident in your assessment, but not absolutely certain. It is unlikely, but not impossible, that you did not understand some parts of the submission or that you are unfamiliar with some pieces of related work.

Soundness

3 good

Presentation

3 good

Contribution

2 fair

Limitations

yes

Reviewer J9bJ2023-08-12

Thank you for your responses. They addressed some of my concerns about the applicability of the proposed framework.

Reviewer 46UP2023-08-15

I thank the authors for their efforts in putting together their rebuttal. I am satisfied with the answers and explanations provided . I raise my score to 6.

Program Chairsdecision2023-09-21

Decision

Accept (poster)

© 2026 NYSGPT2525 LLC