Print Email Facebook Twitter Natural Language Processing and Tabular Data sets in Federated Continual Learning Title Natural Language Processing and Tabular Data sets in Federated Continual Learning: A usability study of FCL in domains beyond Image classification Author Parankusam, Taneshwar Pranav (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Decouchant, Jérémie (mentor) Cox, B.A. (mentor) Wang, Q. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2023-06-30 Abstract Federated Continual Learning (FCL) is a emerging field with strong roots in Image classification. However, limited research has been done on its potential in Natural Language Processing and Tabular datasets. With recent developments in A.I. with language models and the widespread use of mobile devices, it becomes relevant to consider FCL’s capabilities in dynamic environments. Ourpaper discusses and evaluates the applicability of FCL methods between the domains of Natural Language Processing Tabular Data with Image Processing as a baseline. We use Long-Short Term Memory (LSTM) models, DNN’s and LeNet-5 as models for Sentiment analysis, Tabular classification and Image classification. Through our experiments, we evaluate the average accuracy and backwards transfer of EWC, GEM, their federated variants and the state-of-the-art FCL method FedWEIT. With these methods, sentiment analysis and tabular classification tasks show that image classification reached over 17% higher average accuracy and achieved a 99.5% average increase in knowledgetransfer between tasks. Furthermore, we observe that non-federated continual learning methods on average reach higher accuracies than their federatedcounterparts as well as the state-of-the-art methods Subject Federated Continual LearningNatural Language ProcessingTabular DataImage Classification To reference this document use: http://resolver.tudelft.nl/uuid:c64bdc33-c6b5-4497-a476-f06aeb4f6c58 Part of collection Student theses Document type bachelor thesis Rights © 2023 Taneshwar Pranav Parankusam Files PDF CSE3000_Final_Paper_Tanes ... nkusam.pdf 354.97 KB Close viewer /islandora/object/uuid:c64bdc33-c6b5-4497-a476-f06aeb4f6c58/datastream/OBJ/view