CoAst: Validation-Free Contribution Assessment for Federated Learning based on Cross-Round Valuation
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1839-1847
Abstract
In the federated learning (FL) process, since the data held by each participant is different, it is necessary to figure out which participant has a higher contribution to the model performance. Effective contribution assessment can help motivate data owners to participate in the FL training. Research works in this field can be divided into two directions based on whether a validation dataset is required. Validation-based methods need to use representative validation data to measure the model accuracy, which is difficult to obtain in practical FL scenarios. Existing validation-free methods assess the contribution based on the parameters and gradients of local models and the global model in a single training round, which is easily compromised by the stochasticity of model training. In this work, we propose CoAst, a practical method to assess the FL participants' contribution without access to any validation data. The core idea of CoAst involves two aspects: one is to only count the most important part of model parameters through a weights quantization, and the other is a cross-round valuation based on the similarity between the current local parameters and the global parameter updates in several subsequent communication rounds. Extensive experiments show that CoAst has comparable assessment reliability to existing validation-based methods and outperforms existing validation-free methods.Keywords
This publication has 8 references indexed in Scilit:
- Probably Approximate Shapley Fairness with Applications in Machine LearningProceedings of the AAAI Conference on Artificial Intelligence, 2023
- Efficient Participant Contribution Evaluation for Horizontal and Vertical Federated Learning2022
- Data-Free Evaluation of User Contributions in Federated Learning2021
- Game of Gradients: Mitigating Irrelevant Clients in Federated LearningProceedings of the AAAI Conference on Artificial Intelligence, 2021
- Ternary Compression for Communication-Efficient Federated LearningIEEE Transactions on Neural Networks and Learning Systems, 2020
- Measure Contribution of Participants in Federated Learning2019
- Comparison and Modelling of Country-level Microblog User and Activity in Cyber-physical-social Systems Using Weibo and Twitter DataACM Transactions on Intelligent Systems and Technology, 2019
- Deep Residual Learning for Image Recognition2016