MPSL applies parallel split learning with a single aggregated server backward pass to fine-tune multimodal transformers, matching federated learning accuracy while reducing client compute by about 250x.
Parameter- efficient transfer learning for nlp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach
MPSL applies parallel split learning with a single aggregated server backward pass to fine-tune multimodal transformers, matching federated learning accuracy while reducing client compute by about 250x.