paper-with-me

Papers

Prune Your Model Before Distill It

2021-09-30 · Jinhyuk Park, Albert No

Knowledge distillation transfers the knowledge from a cumbersome teacher to a small student. Recent results suggest that the student-friendly teacher is more appropriate to distill since it provides more transferable knowledge. In this work, we propose the novel framework, "prune, then distill," that prunes the model first to make it more transferrable and then distill it to the student. We provide several exploratory examples where the pruned teacher teaches better than the original unpruned networks. We further show theoretically that the pruned teacher plays the role of regularizer in distillation, which reduces the generalization error. Based on this result, we propose a novel neural network compression scheme where the student network is formed based on the pruned teacher and then apply the "prune, then distill" strategy. The code is available at https://github.com/ososos888/prune-then-distill

📄 PDF Abstract BibTeX arXiv:2109.14960

Code (1)

ososos888/prune-then-distill 공식 구현 pytorch

Tasks

Knowledge DistillationmodelNeural Network Compression

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

EPSD: Early Pruning with Self-Distillation for Efficient Model Compression

2024-01-31 · Dong Chen, Ning Liu, Yichen Zhu, Zhengping Che 외

Neural network compression techniques, such as knowledge distillation (KD) and network pruning, have received increasing attention. Recent work `Prune, then Distill' reveals that a pruned student-friendly teacher network…

Knowledge DistillationModel CompressionNetwork PruningNeural Network Compression

Distill the Best, Ignore the Rest: Improving Dataset Distillation with Loss-Value-Based Pruning

2024-11-18 · Brian B. Moser, Federico Raue, Tobias C. Nauen, Stanislav Frolov 외

Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce a novel "Prune First, Di…

Dataset Distillation

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

Automated Channel Pruning with Learned Importance

2021-09-29 · Łukasz Treszczotko, Pawel Kubik

Neural network pruning allows for significant reduction of model size and latency. However, most of the current network pruning methods do not consider channel interdependencies and a lot of manual adjustments are requir…

DenoisingGPUImage DenoisingKnowledge Distillation+1

Self-Distillation with Meta Learning for Knowledge Graph Completion

2023-05-20 · Findings of the Association for Computational Linguistics: EMNLP 2022 2022 12 · Yunshui Li, Junhao Liu, Chengming Li, Min Yang

In this paper, we propose a selfdistillation framework with meta learning(MetaSD) for knowledge graph completion with dynamic pruning, which aims to learn compressed graph embeddings and tackle the longtail samples. Spec…

Knowledge Graph CompletionMeta-LearningTransfer Learning