GeoStack composes multiple domain experts into VLMs with preserved base knowledge and O(1) inference time via geometric stacking and a weight-folding property.
BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Multi-task learning shares information between related tasks, sometimes reducing the number of parameters required. State-of-the-art results across multiple natural language understanding tasks in the GLUE benchmark have previously used transfer from a single large task: unsupervised pre-training with BERT, where a separate BERT model was fine-tuned for each task. We explore multi-task approaches that share a single BERT model with a small number of additional task-specific parameters. Using new adaptation modules, PALs or `projected attention layers', we match the performance of separately fine-tuned models on the GLUE benchmark with roughly 7 times fewer parameters, and obtain state-of-the-art results on the Recognizing Textual Entailment dataset.
verdicts
UNVERDICTED 2representative citing papers
A sequential fine-tuning strategy for pre-trained language models reports modest accuracy gains of 4.7%, 0.99%, and 0.72% on semantic similarity, sequence labeling, and text classification tasks.
citing papers explorer
-
GeoStack: A Framework for Quasi-Abelian Knowledge Composition in VLMs
GeoStack composes multiple domain experts into VLMs with preserved base knowledge and O(1) inference time via geometric stacking and a weight-folding property.
-
To Tune or Not To Tune? How About the Best of Both Worlds?
A sequential fine-tuning strategy for pre-trained language models reports modest accuracy gains of 4.7%, 0.99%, and 0.72% on semantic similarity, sequence labeling, and text classification tasks.