Who Trains Matters: Federated Learning under Enrollment and Participation Selection Biases
Federated learning (FL) trains a shared model from updates contributed by distributed clients, often implicitly assuming that contributing clients are representative of the target population. In practice, this representativeness assumption can fail at two distinct stages, inducing selection bias. First, eligibility rules such as device constraints, software requirements, or user consent determine which clients are ever enrolled and reachable for training, inducing \emph{enrollment bias}. Second, among enrolled clients, user and system factors such as battery state, network status, and local time determine which clients participate in each communication round, inducing \emph{participation bias}. Although existing work has largely addressed round-level participation bias, it has paid far less attention to population-level enrollment bias, which can induce a persistent mismatch between the training objective and the target-population objective. We formalize FL under a two-stage selection model and derive \textsc{FedIPW}, an inverse-probability-weighted aggregation scheme that recovers the target-population mean update under standard ignorability and positivity assumptions. Because client-level covariates are often unavailable for non-enrolled clients, we also introduce a limited-information aggregate-calibration extension that uses known target-population summaries to reweight the enrolled sample, partially correcting enrollment bias. We further provide an algorithm-agnostic optimization analysis under residual weighting error and show that incomplete selection correction can induce a non-vanishing bias floor. Finally, experiments on synthetic federated logistic regression validate the predicted objective mismatch and show that enrollment correction reduces target-population error under two-stage selection.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningSimilar Papers 제목 키워드 기반
Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Review
Federated Learning (FL) is a learning mechanism that falls under the distributed training umbrella, which collaboratively trains a shared global model without disclosing the raw data from different clients. This paper pr…
FairnessFederated LearningSurveyUnderstanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
Existing works in federated learning (FL) often assume an ideal system with either full client or uniformly distributed client participation. However, in practice, it has been observed that some clients may never partici…
Federated LearningOn the Convergence of Federated Averaging with Cyclic Client Participation
Federated Averaging (FedAvg) and its variants are the most popular optimization algorithms in federated learning (FL). Previous convergence analyses of FedAvg either assume full client participation or partial client par…
Federated LearningTackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal
Federated Learning is a fast growing area of ML where the training datasets are extremely distributed, all while dynamically changing over time. Models need to be trained on clients' devices without any guarantees for ei…
Federated LearningIncremental LearningEmbracing Federated Learning: Enabling Weak Client Participation via Partial Model Training
In Federated Learning (FL), clients may have weak devices that cannot train the full model or even hold it in their memory space. To implement large-scale FL applications, thus, it is crucial to develop a distributed lea…
Federated Learning