paper-with-me

홈 › Papers

Investigating Transferability in Pretrained Language Models

2020-04-30 · Findings of the Association for Computational Linguistics 2020 · Alex Tamkin, Trisha Singh, Davide Giovanardi, Noah Goodman

How does language model pretraining help transfer learning? We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance. This method, partial reinitialization, involves replacing different layers of a pretrained model with random weights, then finetuning the entire model on the transfer task and observing the change in performance. This technique reveals that in BERT, layers with high probing performance on downstream GLUE tasks are neither necessary nor sufficient for high accuracy on those tasks. Furthermore, the benefit of using pretrained parameters for a layer varies dramatically with finetuning dataset size: parameters that provide tremendous performance improvement when data is plentiful may provide negligible benefits in data-scarce settings. These results reveal the complexity of the transfer learning process, highlighting the limitations of methods that operate on frozen models or single data samples.

📄 PDF Abstract BibTeX arXiv:2004.14975

Code (1)

dgiova/bert-lm-transferability 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingTransfer Learning

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adam 설명 없음

Similar Papers 제목 키워드 기반

PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks

2022-03-10 · Nan Ding, Xi Chen, Tomer Levinboim, Beer Changpinyo 외

With the increasing abundance of pretrained models in recent years, the problem of selecting the best pretrained checkpoint for a particular downstream classification task has been gaining increased attention. Although s…

Learning TheoryModel SelectionTransferabilityTransfer Learning

Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models

2023-07-26 · ICCV 2023 1 · Dong Lu, Zhiqiang Wang, Teng Wang, Weili Guan 외

Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred to attack other black-box models. However…

Image-text RetrievalRetrievalText Retrieval

Towards Understanding the Transferability of Deep Representations

2019-09-26 · Hong Liu, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in r…

One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs

2025-12-14 · Yixin Tan, Zhe Yu, Jun Sakuma arxiv

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs…

Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer

2023-09-19 · Fei Wang, Kuan-Hao Huang, Kai-Wei Chang, Muhao Chen

Zero-shot cross-lingual transfer is a central task in multilingual NLP, allowing models trained in languages with more sufficient training resources to generalize to other low-resource languages. Earlier efforts on this …

Cross-Lingual TransferMultilingual NLPZero-Shot Cross-Lingual Transfer