Reducing Communication Overhead in Federated Learning for Pre-trained Language Models Using Parameter-Efficient Finetuning.
Shubham MalaviyaManish ShuklaSachin LodhaPublished in: CoLLAs (2023)
Keyphrases
- language model
- communication overhead
- learning algorithm
- reinforcement learning
- learning process
- prior knowledge
- relevance model
- pre trained
- document retrieval
- information retrieval systems
- retrieval model
- query expansion
- unsupervised learning
- machine learning
- probabilistic model
- active learning
- information retrieval