DRILL: Dynamic Representations for Imbalanced Lifelong Learning

<p>Continual or lifelong learning has been a long-standing challenge in machine learning to date, especially in natural language processing (NLP). Although state-of-the-art language models such as BERT have ushered in a new era in this field due to their outstanding performance in multitask learning scenarios, they suffer from forgetting when being exposed to a continuous stream of non-stationary data. In this paper, we introduce DRILL, a novel lifelong learning architecture for open-domain sequence classification. DRILL leverages a biologically inspired self-organizing neural architecture to selectively gate latent language representations from BERT in a domain-incremental fashion. We demonstrate in our experiments that DRILL outperforms current methods in a realistic scenario of imbalanced classification from a data stream without prior knowledge about task or dataset boundaries. To the best of our knowledge, DRILL is the first of its kind to use a self-organizing neural architecture for open-domain lifelong learning in NLP.</p>

@InProceedings{AAW21, 
 	 author =  {Ahrens, Kyra and Abawi, Fares and Wermter, Stefan},  
 	 title = {DRILL: Dynamic Representations for Imbalanced Lifelong Learning}, 
 	 booktitle = {Proceedings of the 30th International Conference on Artificial Neural Networks (ICANN 2021)},
 	 editors = {Igor Farkaš, Paolo Masulli, Sebastian Otte, Stefan Wermter},
 	 number = {},
 	 volume = {},
 	 pages = {409--420},
 	 year = {2021},
 	 month = {Sep},
 	 publisher = {Springer International Publishing},
 	 doi = {10.1007/978-3-030-86340-1_33}, 
 }