Federated Learning Based Multilingual Emoji Prediction In Clean and Attack Scenarios

TL;DR

This paper explores federated learning for multilingual emoji prediction, demonstrating that it performs comparably to centralized models even under attack scenarios, while preserving user privacy.

Contribution

It introduces a federated learning framework for multilingual emoji prediction, including robustness against label-flipping attacks and evaluation on real-world datasets.

Findings

Federated learning achieves similar accuracy to centralized models in emoji prediction.

Models are robust against label-flipping attacks in federated settings.

Federated approach outperforms other techniques on SemEval emoji dataset.

Abstract

Federated learning is a growing field in the machine learning community due to its decentralized and private design. Model training in federated learning is distributed over multiple clients giving access to lots of client data while maintaining privacy. Then, a server aggregates the training done on these multiple clients without access to their data, which could be emojis widely used in any social media service and instant messaging platforms to express users' sentiments. This paper proposes federated learning-based multilingual emoji prediction in both clean and attack scenarios. Emoji prediction data have been crawled from both Twitter and SemEval emoji datasets. This data is used to train and evaluate different transformer model sizes including a sparsely activated transformer with either the assumption of clean data in all clients or poisoned data via label flipping attack in some clients. Experimental results on these models show that federated learning in either clean or attacked scenarios performs similarly to centralized training in multilingual emoji prediction on seen and unseen languages under different data sources and distributions. Our trained transformers perform better than other techniques on the SemEval emoji dataset in addition to the privacy as well as distributed benefits of federated learning.