Papers with Intermediate Layer Distillation

3 papers
Revisiting Intermediate Layer Distillation for Compressing Language Models: An Overfitting Perspective (2023.findings-eacl)

Copied to clipboard

Challenge: Existing methods for knowledge distillation (KD) are prone to overfitting to training datasets . recent advances in NLP have shown that using PLMs such as BERT and RoBERTa on downstream tasks is effective.
Approach: They propose a consistency-regularized knowledge distillation method which mitigates overfitting of existing methods.
Outcome: The proposed method outperforms existing methods on the GLUE benchmark and synthetic datasets.
CILDA: Contrastive Data Augmentation Using Intermediate Layer Knowledge Distillation (2022.coling-1)

Copied to clipboard

Challenge: Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models.
Approach: They propose a data augmentation technique tailored for knowledge distillation based on contrastive loss to improve masked adversarial data augmented by intermediate layer matching.
Outcome: The proposed technique outperforms state-of-the-art methods on the GLUE benchmark and in an out-of domain evaluation.
Intermediate Layer Distillation with the Reused Teacher Classifier: A Study on the Importance of the Classifier of Attention-based Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing methods underestimate the importance of utilizing the teacher's discriminative classifier and face challenges in establishing proper layer mappings.
Approach: They propose to reuse pre-trained teacher classifiers to improve student performance . they use projectors to match hidden size of the teacher model to student .
Outcome: The proposed method outperforms existing methods on 97.7% of the teacher BERT base without additional trainable parameters.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations