Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Task-specific Compression for Multi-task Language Models using Attribution-based Pruning

About

Multi-task language models show outstanding performance for various natural language understanding tasks with only a single model. However, these language models utilize an unnecessarily large number of model parameters, even when used only for a specific task. This paper proposes a novel training-free compression method for multi-task language models using a pruning method. Specifically, we use an attribution method to determine which neurons are essential for performing a specific task. We task-specifically prune unimportant neurons and leave only task-specific parameters. Furthermore, we extend our method to be applicable in low-resource and unsupervised settings. Since our compression method is training-free, it uses few computing resources and does not destroy the pre-trained knowledge of language models. Experimental results on the six widely-used datasets show that our proposed pruning method significantly outperforms baseline pruning methods. In addition, we demonstrate that our method preserves performance even in an unseen domain setting.

Nakyeong Yang, Yunah Jang, Hwanhee Lee, Seohyeong Jung, Kyomin Jung• 2022

Related benchmarks

TaskDatasetResultRank
Visual ReasoningCommonsense Reasoning
Jaccard Index (J)6.95
30
Visual ReasoningPhysical Reasoning
J Score8.07
30
Visual ReasoningQuantitative Reasoning
J Score6.94
30
Visual Grounded Reasoning AnalysisPhysical domain dataset
Grounding Score5.6
5
Logit Divergence AnalysisPhysical reasoning domain (calibration set)
Mean KL Divergence (nats)10.51
5
Showing 5 of 5 rows

Other info

Follow for update