REVIEW 3 cited by
Federated Learning on Non-IID Data Silos: An Experimental Study
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Due to the increasing privacy concerns and data regulations, training data have been increasingly fragmented, forming distributed databases of multiple "data silos" (e.g., within different organizations and countries). To develop effective machine learning services, there is a must to exploit data from such distributed databases without exchanging the raw data. Recently, federated learning (FL) has been a solution with growing interests, which enables multiple parties to collaboratively train a machine learning model without exchanging their local data. A key and common challenge on distributed databases is the heterogeneity of the data distribution among the parties. The data of different parties are usually non-independently and identically distributed (i.e., non-IID). There have been many FL algorithms to address the learning effectiveness under non-IID data settings. However, there lacks an experimental study on systematically understanding their advantages and disadvantages, as previous studies have very rigid data partitioning strategies among parties, which are hardly representative and thorough. In this paper, to help researchers better understand and study the non-IID data setting in federated learning, we propose comprehensive data partitioning strategies to cover the typical non-IID data cases. Moreover, we conduct extensive experiments to evaluate state-of-the-art FL algorithms. We find that non-IID does bring significant challenges in learning accuracy of FL algorithms, and none of the existing state-of-the-art FL algorithms outperforms others in all cases. Our experiments provide insights for future studies of addressing the challenges in "data silos".
Forward citations
Cited by 3 Pith papers
-
Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity
Sparse zeroth-order federated fine-tuning with shared seeds and GradIP-based early stopping matches or beats full-parameter ZO while using far less communication.
-
Efficient Federated Learning with Timely Update Dissemination
FedASMU and FedSSMU improve federated learning accuracy and speed by dynamically disseminating fresh global models to devices during local training, using server-side and device-side adaptive weighting.
-
Fairness in Federated Learning: Trends, Challenges, and Opportunities
A survey of fairness in federated learning: bias sources, mitigation algorithms, evaluation metrics, and open problems.
Discussion (0). Sign in to comment.