DC10 Project: Enhancing NLP Capabilities through Federated Learning and GNNs

PhD Supervisor: Prof. Carlo Nitsch (UNINA); Auxiliary supervisors: David Camacho (UPM), Dariusz Mrozek (SUT), Shen Yin (NTNU); R&D cooperation: ALMAWAVE

Objectives: The aim of this research project will be to integrate Natural Language Processing (NLP) within the framework of federated learning and Graph Neural Networks (GNNs). The primary objectives are to: (i) develop Federated NLP Models: To design and implement NLP models that can operate effectively in a federated learning context, ensuring data privacy and security across decentralised nodes; (ii) incorporate GNNs into the NLP processes: To explore and enhance the use of GNNs in processing complex linguistic structures, thereby improving the understanding and generation of natural language in a decentralised setting; (iii) address the challenges in Federated NLP: To investigate and overcome the specific challenges that are associated with NLP in federated environments, such as maintaining model performance with decentralised, heterogeneous data sources.

Expected Results: By the end of this project, the following outcomes are anticipated:

Federated NLP Models: NLP models that are capable of operating across decentralised networks, maintaining data privacy and achieving comparable performance to centralised models will be developed; GNN-Enhanced Language Processing: Advanced methodologies that utilise GNNs for better handling and interpretation of complex language structures in a federated setting will be developed; Insights and Best Practices: Comprehensive understanding of the challenges and solutions in federated NLP, which will contribute to the broader field of AI by providing guidelines for future research and implementations will be developed; This project goal of the Doctoral Network by merging NLP with federated learning and GNNs, thereby advancing the transparency, openness and explainability of AI systems in processing natural language.

Applied research: The focus is on integrating Natural Language Processing (NLP) with federated learning and Graph Neural Networks (GNNs) for decentralized data processing. The project targets the development of privacy-preserving NLP models suitable for decentralized networks, ensuring secure, efficient language processing. It also aims to advance the use of GNNs in NLP, tackling complex linguistic structures in decentralized environments. The anticipated outcomes include practical federated NLP models, GNN-enhanced linguistic processing techniques, and comprehensive insights into federated NLP challenges, guiding future AI research towards more transparent and understandable natural language systems.

Planned secondments: UPM(4 months); SUT(4 months); NTNU (4 months)                   

Enrolment in Doctoral degree: UNINA

Recruitment of Doctoral Candidate: https://euraxess.ec.europa.eu/jobs/290127