Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers
Abstract
Multilingual transformer-based models demonstrate remarkable zero and few-shot transfer across languages by learning and reusing language-agnostic features. However, as a fixed-size model acquires more languages, its performance across all languages degrades, a phenomenon termed interference. Often attributed to limited model capacity, interference is commonly addressed by adding additional parameters despite evidence that transformer-based models are overparameterized. In this work, we show that it is possible to reduce interference by instead identifying and pruning language-specific parameters. First, we use Shapley Values, a credit allocation metric from coalitional game theory, to identify attention heads that introduce interference. Then, we show that removing identified attention heads from a fixed model improves performance for a target language on both sentence classification and structural prediction, seeing gains as large as 24.7\%. Finally, we provide insights on language-agnostic and language-specific attention heads using attention visualization.
- Publication:
-
arXiv e-prints
- Pub Date:
- October 2022
- DOI:
- 10.48550/arXiv.2210.05709
- arXiv:
- arXiv:2210.05709
- Bibcode:
- 2022arXiv221005709H
- Keywords:
-
- Computer Science - Computation and Language;
- Computer Science - Machine Learning
- E-Print:
- 8 Pages, 9 Figures