Towards Federated Long-Tailed Learning
This addresses the challenge of class imbalance and data privacy in machine learning applications, but it is incremental as it primarily characterizes scenarios without presenting a novel solution.
The paper tackles the combined problem of learning from long-tailed data distributions within a federated learning framework, highlighting three scenarios with different local or global imbalances and noting that preliminary results indicate significant future work is needed to resolve these tasks.
Data privacy and class imbalance are the norm rather than the exception in many machine learning tasks. Recent attempts have been launched to, on one side, address the problem of learning from pervasive private data, and on the other side, learn from long-tailed data. However, both assumptions might hold in practical applications, while an effective method to simultaneously alleviate both issues is yet under development. In this paper, we focus on learning with long-tailed (LT) data distributions under the context of the popular privacy-preserved federated learning (FL) framework. We characterize three scenarios with different local or global long-tailed data distributions in the FL framework, and highlight the corresponding challenges. The preliminary results under different scenarios reveal that substantial future work are of high necessity to better resolve the characterized federated long-tailed learning tasks.