paper-with-me

Papers

XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation

2021-06-08 · Subhabrata Mukherjee, Ahmed Hassan Awadallah, Jianfeng Gao

While deep and large pre-trained models are the state-of-the-art for various natural language processing tasks, their huge size poses significant challenges for practical uses in resource constrained settings. Recent works in knowledge distillation propose task-agnostic as well as task-specific methods to compress these models, with task-specific ones often yielding higher compression rate. In this work, we develop a new task-agnostic distillation framework XtremeDistilTransformers that leverages the advantage of task-specific methods for learning a small universal model that can be applied to arbitrary tasks and languages. To this end, we study the transferability of several source tasks, augmentation resources and model architecture for distillation. We evaluate our model performance on multiple tasks, including the General Language Understanding Evaluation (GLUE) benchmark, SQuAD question answering dataset and a massive multi-lingual NER dataset with 41 languages. We release three distilled task-agnostic checkpoints with 13MM, 22MM and 33MM parameters obtaining SOTA performance in several tasks.

📄 PDF Abstract BibTeX arXiv:2106.04563

Code (1)

microsoft/xtreme-distil-transformers 공식 구현 tf

Tasks

Knowledge DistillationNERQuestion Answering

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Generic-to-Specific Distillation of Masked Autoencoders

2023-02-28 · CVPR 2023 1 · Wei Huang, Zhiliang Peng, Li Dong, Furu Wei 외

Large vision Transformers (ViTs) driven by self-supervised pre-training mechanisms achieved unprecedented progress. Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training me…

Decoderimage-classificationImage ClassificationKnowledge Distillation+3

Why Can You Lay Off Heads? Investigating How BERT Heads Transfer

2021-06-14 · Ting-Rui Chiang, Yun-Nung Chen

The huge size of the widely used BERT family models has led to recent efforts about model distillation. The main goal of distillation is to create a task-agnostic pre-trained model that can be fine-tuned on downstream ta…

Transfer Learning

A Comparative Analysis of Task-Agnostic Distillation Methods for Compressing Transformer Language Models

2023-10-13 · Takuma Udagawa, Aashka Trivedi, Michele Merler, Bishwaranjan Bhattacharjee

Large language models have become a vital component in modern NLP, achieving state of the art performance in a variety of tasks. However, they are often inefficient for real-world deployment due to their expensive infere…

Knowledge Distillation

HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers

2023-02-19 · Chen Liang, Haoming Jiang, Zheng Li, Xianfeng Tang 외

Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a c…

Knowledge DistillationModel CompressionTransfer Learning

Multi-level Knowledge Distillation via Knowledge Alignment and Correlation

2020-12-01 · Fei Ding, Yin Yang, Hongxin Hu, Venkat Krovi 외

Knowledge distillation (KD) has become an important technique for model compression and knowledge transfer. In this work, we first perform a comprehensive analysis of the knowledge transferred by different KD methods. We…

Contrastive LearningKnowledge DistillationModel CompressionTransfer Learning