Short text clustering has been popularly studied for its significance in mining valuable insights from many short texts. In this paper, we focus on the federated short text clustering (FSTC) problem, i.e., clustering short texts that are distributed in different clients, which is a realistic problem under privacy requirements. Compared with the centralized short text clustering problem that short texts are stored on a central server, the FSTC problem has not been explored yet. To fill this gap, we propose a Federated Robust Short Text Clustering (FSTC) framework. FSTC includes two main modules, i.e., robust short text clustering module and federated cluster center aggregation module. The robust short text clustering module aims to train an effective short text clustering model with local data in each client. We innovatively combine optimal transport to generate pseudo-labels with Gaussian-uniform mixture model to ensure the reliability of the pseudo-supervised data. The federated cluster center aggregation module aims to exchange knowledge across clients without sharing local raw data in an efficient way. The server aggregates the local cluster centers from different clients and then sends the global centers back to all clients in each communication round. Our empirical studies on three short text clustering datasets demonstrate that FSTC significantly outperforms the federated short text clustering baselines.

本文提出了一种面向分布式短文本聚类的联邦鲁棒短文本聚类（FSTC）框架，该框架通过创新地将最优输运与高斯-均匀混合模型相结合，旨在以有效的数据训练模型并确保伪有监督数据的可靠性，在客户端间以高效的方式交换知识而不共享原始数据，从而显著优于基准联邦短文本聚类方法。

短文本聚类的联邦学习