Adapters: Data & compute efficient fine-tuning of Transformers – Alexandra Lindt

We are happy to welcome you to another AI paper discussion group, where we will cover AI related papers to keep up to date with what is happening in this fast moving field!

Alexandra Lindt, Machine Learning Researcher at Merantix Momentum, will talk about:

####################################################
Adapters:
Data and compute efficient fine-tuning of Transformers
####################################################

Some relevant references about this topic:
Parameter-Efficient Transfer Learning for NLP
-> https://arxiv.org/abs/1902.00751
AdapterFusion: Non-Destructive Task Composition for Transfer Learning
-> https://arxiv.org/abs/2005.00247
AdapterDrop: On the Efficiency of Adapters in Transformers
-> https://arxiv.org/abs/2010.11918

Looking forward to seeing you there and discuss this topic in more detail!