Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability

• URL: http://arxiv.org/abs/2203.05180v1
• Date: Thu, 10 Mar 2022 06:23:41 GMT
• Title: Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability
• Authors: Ruifei He, Shuyang Sun, Jihan Yang, Song Bai and Xiaojuan Qi
• Abstract summary: Knowledge Distillation as Efficient Pre-training aims to efficiently transfer the learned feature representation from pre-trained models to new student models for future downstream tasks. Our method performs comparably with supervised pre-training counterparts in 3 downstream tasks and 9 downstream datasets requiring 10x less data and 5x less pre-training time.
• Score: 53.27240222619834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale pre-training has been proven to be crucial for various computer vision tasks. However, with the increase of pre-training data amount, model architecture amount, and the private/inaccessible data, it is not very efficient or possible to pre-train all the model architectures on large-scale datasets. In this work, we investigate an alternative strategy for pre-training, namely Knowledge Distillation as Efficient Pre-training (KDEP), aiming to efficiently transfer the learned feature representation from existing pre-trained models to new student models for future downstream tasks. We observe that existing Knowledge Distillation (KD) methods are unsuitable towards pre-training since they normally distill the logits that are going to be discarded when transferred to downstream tasks. To resolve this problem, we propose a feature-based KD method with non-parametric feature dimension aligning. Notably, our method performs comparably with supervised pre-training counterparts in 3 downstream tasks and 9 downstream datasets requiring 10x less data and 5x less pre-training time. Code is available at https://github.com/CVMI-Lab/KDEP.

Related papers

• Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks [19.941727879841142]
  We propose a novel underlineDelayed underlineBottlenecking underlinePre-training framework. It maintains as much as possible mutual information between latent representations and training data during pre-training phase.
  arXiv  Detail & Related papers  (2024-04-23T11:35:35Z)
• Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding [9.655434542591815]
  Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples.
  arXiv  Detail & Related papers  (2023-12-08T19:26:13Z)
• Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks [39.71761440499148]
  Pre-training on graph neural networks (GNNs) aims to learn transferable knowledge for downstream tasks with unlabeled data. We propose a better-with-less framework for graph pre-training: fewer, but carefully chosen data are fed into a GNN model. Experiment results show that the proposed APT is able to obtain an efficient pre-training model with fewer training data and better downstream performance.
  arXiv  Detail & Related papers  (2023-11-02T07:09:59Z)
• Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening [51.34904967046097]
  Selective Synaptic Dampening (SSD) is a fast, performant, and does not require long-term storage of the training data. We present a novel two-step, post hoc, retrain-free approach to machine unlearning which is fast, performant, and does not require long-term storage of the training data.
  arXiv  Detail & Related papers  (2023-08-15T11:30:45Z)
• Optimal transfer protocol by incremental layer defrosting [66.76153955485584]
  Transfer learning is a powerful tool enabling model training with limited amounts of data. The simplest transfer learning protocol is based on freezing" the feature-extractor layers of a network pre-trained on a data-rich source task. We show that this protocol is often sub-optimal and the largest performance gain may be achieved when smaller portions of the pre-trained network are kept frozen.
  arXiv  Detail & Related papers  (2023-03-02T17:32:11Z)
• Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
  We propose self-distillation as a regularization for a further pre-training stage. We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
  arXiv  Detail & Related papers  (2022-09-30T02:25:12Z)
• Self-Supervised Pretraining Improves Self-Supervised Pretraining [83.1423204498361]
  Self-supervised pretraining requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. This paper explores Hierarchical PreTraining (HPT), which decreases convergence time and improves accuracy by initializing the pretraining process with an existing pretrained model. We show HPT converges up to 80x faster, improves accuracy across tasks, and improves the robustness of the self-supervised pretraining process to changes in the image augmentation policy or amount of pretraining data.
  arXiv  Detail & Related papers  (2021-03-23T17:37:51Z)
• Efficient Conditional Pre-training for Transfer Learning [71.01129334495553]
  We propose efficient filtering methods to select relevant subsets from the pre-training dataset. We validate our techniques by pre-training on ImageNet in both the unsupervised and supervised settings. We improve standard ImageNet pre-training by 1-3% by tuning available models on our subsets and pre-training on a dataset filtered from a larger scale dataset.
  arXiv  Detail & Related papers  (2020-11-20T06:16:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.