RECORD
Game of Gradients: Mitigating Irrelevant Clients in Federated Learning
Machine Learning · Submitted 23 Oct 2021
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim We finally conduct a thorough empirical analysis on image classification and speech recognition tasks to show the superior performance of S-FedAvg than the baselines in the context of supervised federated learning settings.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
The paradigm of Federated learning (FL) deals with multiple clients participating in collaborative training of a machine learning model under the orchestration of a central server. In this setup, each client's data is private to itself and is not transferable to other clients or the server. Though FL paradigm has received significant interest recently from the research community, the problem of selecting the relevant clients w.r.t. the central server's learning objective is under-explored. We refer to these problems as Federated Relevant Client Selection (FRCS). Because the server doesn't have explicit control over the nature of data possessed by each client, the problem of selecting relevant clients is significantly complex in FL settings. In this paper, we resolve important and related FRCS problems viz., selecting clients with relevant data, detecting clients that possess data relevant to a particular target label, and rectifying corrupted data samples of individual clients. We follow a principled approach to address the above FRCS problems and develop a new federated learning method using the Shapley value concept from cooperative game theory. Towards this end, we propose a cooperative game involving the gradients shared by the clients. Using this game, we compute Shapley values of clients and then present Shapley value based Federated Averaging (S-FedAvg) algorithm that empowers the server to select relevant clients with high probability. S-FedAvg turns out to be critical in designing specific algorithms to address the FRCS problems. We finally conduct a thorough empirical analysis on image classification and speech recognition tasks to show the superior performance of S-FedAvg than the baselines in the context of supervised federated learning settings.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | The paradigm of Federated learning (FL) deals with multiple clients participating in collaborative training of a machine learning model under the orchestration of a central server. | background 1.00 | 0.04 | 0.02 | asserted 1.00 |
| s1 | In this setup, each client's data is private to itself and is not transferable to other clients or the server. | background 1.00 | 0.04 | 0.01 | asserted 1.00 |
| s2 | Though FL paradigm has received significant interest recently from the research community, the problem of selecting the relevant clients w.r.t. the central server's learning objective is under-explored. | gap 1.00 | 0.06 | 0.03 | asserted 0.99 |
| s3 | We refer to these problems as Federated Relevant Client Selection (FRCS). | background 0.81 | 0.29 | 0.03 | asserted 0.91 |
| s4 | Because the server doesn't have explicit control over the nature of data possessed by each client, the problem of selecting relevant clients is significantly complex in FL settings. | background 0.90 | 0.06 | 0.02 | asserted 1.00 |
| s5 | In this paper, we resolve important and related FRCS problems viz., selecting clients with relevant data, detecting clients that possess data relevant to a particular target label, and rectifying corrupted data samples of individual clients. | contribution 1.00 | 0.81 | 0.15 | asserted 1.00 |
| s6 | We follow a principled approach to address the above FRCS problems and develop a new federated learning method using the Shapley value concept from cooperative game theory. | contribution 0.52 | 0.93 | 0.09 | asserted 0.99 |
| s7 | Towards this end, we propose a cooperative game involving the gradients shared by the clients. | method 0.97 | 0.85 | 0.03 | asserted 0.95 |
| s8 | Using this game, we compute Shapley values of clients and then present Shapley value based Federated Averaging (S-FedAvg) algorithm that empowers the server to select relevant clients with high probability. | method 0.84 | 0.94 | 0.20 | asserted 0.62 |
| s9 | S-FedAvg turns out to be critical in designing specific algorithms to address the FRCS problems. | interpretation 0.62 | 0.57 | 0.10 | asserted 0.99 |
| s10 | We finally conduct a thorough empirical analysis on image classification and speech recognition tasks to show the superior performance of S-FedAvg than the baselines in the context of supervised federated learning settings. | result 0.87 | 0.96 | 0.74 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
The paradigm of Federated learning (FL) deals with multiple clients participating in collaborative training of a machine learning model under the orchestration of a central server. In this setup, each client's data is private to itself and is not transferable to other clients or the server. Though FL paradigm has received significant interest recently from the research community, the problem of selecting the relevant clients w.r.t. the central server's learning objective is under-explored. We refer to these problems as Federated Relevant Client Selection (FRCS). Because the server doesn't have explicit control over the nature of data possessed by each client, the problem of selecting relevant clients is significantly complex in FL settings. In this paper, we resolve important and related FRCS problems viz., selecting clients with relevant data, detecting clients that possess data relevant to a particular target label, and rectifying corrupted data samples of individual clients. We follow a principled approach to address the above FRCS problems and develop a new federated learning method using the Shapley value concept from cooperative game theory. Towards this end, we propose a cooperative game involving the gradients shared by the clients. Using this game, we compute Shapley values of clients and then present Shapley value based Federated Averaging (S-FedAvg) algorithm that empowers the server to select relevant clients with high probability. S-FedAvg turns out to be critical in designing specific algorithms to address the FRCS problems. We finally conduct a thorough empirical analysis on image classification and speech recognition tasks to show the superior performance of S-FedAvg than the baselines in the context of supervised federated learning settings.
Human review
How the literature uses it
What this paper does with the arXiv papers it cites
What it cites · 2 sentences without a confident label
Cites as background 2 papers
-
On privacy aspect, many solutions are proposed to provide strong privacy guarantees that protect the confidentiality of the clients' data [ref] .
Differentially Private Federated Learning: A Client Level Perspective · Related Work · 0.91
-
On privacy aspect, many solutions are proposed to provide strong privacy guarantees that protect the confidentiality of the clients' data [ref] .
Blockchained On-Device Federated Learning · Related Work · 0.91
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.