paper-with-me

Papers

Annealing Knowledge Distillation

2021-04-14 · EACL 2021 2 · Aref Jafari, Mehdi Rezagholizadeh, Pranav Sharma, Ali Ghodsi

Significant memory and computational requirements of large deep neural networks restrict their application on edge devices. Knowledge distillation (KD) is a prominent model compression technique for deep neural networks in which the knowledge of a trained large teacher model is transferred to a smaller student model. The success of knowledge distillation is mainly attributed to its training objective function, which exploits the soft-target information (also known as "dark knowledge") besides the given regular hard labels in a training set. However, it is shown in the literature that the larger the gap between the teacher and the student networks, the more difficult is their training using knowledge distillation. To address this shortcoming, we propose an improved knowledge distillation method (called Annealing-KD) by feeding the rich information provided by the teacher's soft-targets incrementally and more efficiently. Our Annealing-KD technique is based on a gradual transition over annealed soft-targets generated by the teacher at different temperatures in an iterative process, and therefore, the student is trained to follow the annealed teacher output in a step-by-step manner. This paper includes theoretical and empirical evidence as well as practical experiments to support the effectiveness of our Annealing-KD method. We did a comprehensive set of experiments on different tasks such as image classification (CIFAR-10 and 100) and NLP language inference with BERT-based models on the GLUE benchmark and consistently got superior results.

📄 PDF Abstract BibTeX arXiv:2104.07163

Code (1)

huawei-noah/KD-NLP/tree/main/Annealing_KD pytorch

Tasks

image-classificationImage ClassificationKnowledge DistillationModel 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

Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation

2024-09-30 · Vlad-Cristian Matei, Iulian-Marius Tăiatu, Răzvan-Alexandru Smădu, Dumitru-Clementin Cercel

This paper highlights the significance of natural language processing (NLP) within artificial intelligence, underscoring its pivotal role in comprehending and modeling human language. Recent advancements in NLP, particul…

Data AugmentationKnowledge DistillationMulti-Task Learning

BAM! Born-Again Multi-Task Networks for Natural Language Understanding

2019-07-10 · ACL 2019 7 · Kevin Clark, Minh-Thang Luong, Urvashi Khandelwal, Christopher D. Manning 외

It can be challenging to train multi-task neural networks that outperform or even match their single-task counterparts. To help address this, we propose using knowledge distillation where single-task models teach a multi…

Knowledge DistillationNatural Language Understanding

A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation

2018-10-29 · ICLR 2019 5 · Akhilesh Gotmare, Nitish Shirish Keskar, Caiming Xiong, Richard Socher

The convergence rate and final performance of common deep learning models have significantly benefited from heuristics such as learning rate schedules, knowledge distillation, skip connections, and normalization layers. …

Dimensionality ReductionKnowledge Distillation

Transfer of Knowledge through Reverse Annealing: A Preliminary Analysis of the Benefits and What to Share

2025-01-27 · Eneko Osaba, Esther Villar-Rodriguez

Being immersed in the NISQ-era, current quantum annealers present limitations for solving optimization problems efficiently. To mitigate these limitations, D-Wave Systems developed a mechanism called Reverse Annealing, a…

BenchmarkingTransfer Learning

Annealing Self-Distillation Rectification Improves Adversarial Training

2023-05-20 · Yu-Yu Wu, Hung-Jui Wang, Shang-Tse Chen

In standard adversarial training, models are optimized to fit one-hot labels within allowable adversarial perturbation budgets. However, the ignorance of underlying distribution shifts brought by perturbations causes the…

Adversarial Robustness