English
Related papers

Related papers: Weight Squeezing: Reparameterization for Knowledge…

200 papers

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…

Computation and Language · Computer Science 2024-07-04 Ying Zhang , Ziheng Yang , Shufan Ji

Communication overhead severely hinders the scalability of distributed machine learning systems. Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-05-19 Yuchen Zhong , Cong Xie , Shuai Zheng , Haibin Lin

In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing knowledge transfer methods (e.g., backbone sharing, knowledge distillation) often hinge on shared…

Machine Learning · Computer Science 2024-12-30 Kunxi Li , Tianyu Zhan , Kairui Fu , Shengyu Zhang , Kun Kuang , Jiwei Li , Zhou Zhao , Fan Wu , Fei Wu

This paper proposes a novel garment transfer method supervised with knowledge distillation from virtual try-on. Our method first reasons the transfer parsing to provide shape prior to downstream tasks. We employ a multi-phase teaching…

Computer Vision and Pattern Recognition · Computer Science 2024-04-05 Naiyu Fang , Lemiao Qiu , Shuyou Zhang , Zili Wang , Kerui Hu , Jianrong Tan

Transfer learning aims to leverage knowledge from pre-trained models to benefit the target task. Prior transfer learning work mainly transfers from a single model. However, with the emergence of deep models pre-trained from different…

Machine Learning · Computer Science 2022-11-07 Yang Shu , Zhangjie Cao , Ziyang Zhang , Jianmin Wang , Mingsheng Long

The success of self-attention lies in its ability to capture long-range dependencies and enhance context understanding, but it is limited by its computational complexity and challenges in handling sequential data with inherent…

Computation and Language · Computer Science 2025-05-05 Md Kowsher , Nusrat Jahan Prottasha , Chun-Nam Yu , Ozlem Ozmen Garibay , Niloofar Yousefi

We introduce a simple yet effective method of integrating contextual embeddings with commonsense graph embeddings, dubbed BERT Infused Graphs: Matching Over Other embeDdings. First, we introduce a preprocessing method to improve the speed…

Computation and Language · Computer Science 2019-10-18 Jeff Da

Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple…

Computation and Language · Computer Science 2024-06-07 Zhisheng Lin , Han Fu , Chenghao Liu , Zhuo Li , Jianling Sun

In this paper, we propose a method for transferring feature representation to lightweight student models from larger teacher models. We mathematically define a new notion called \textit{perception coherence}. Based on this notion, we…

Machine Learning · Statistics 2026-02-24 Hai-Vy Nguyen , Fabrice Gamboa , Sixin Zhang , Reda Chhaibi , Serge Gratton , Thierry Giaccone

Model merging has emerged as a promising solution to accommodate multiple large models within constrained memory budgets. We present StatsMerging, a novel lightweight learning-based model merging method guided by weight distribution…

Machine Learning · Computer Science 2025-06-06 Ranjith Merugu , Bryan Bo Cao , Shubham Jain

Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity significantly impact inference speed, limiting its application on terminal medical…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Yineng Chen , Peng Huang , Aozhong Zhang , Hui Guo , Penghang Yin , Shu Hu , Shao Lin , Xin Li , Tzu-Jen Kao , Balakrishnan Prabhakaran , MingChing Chang , Xin Wang

Deep neural network compression techniques such as pruning and weight tensor decomposition usually require fine-tuning to recover the prediction accuracy when the compression ratio is high. However, conventional fine-tuning suffers from the…

Machine Learning · Computer Science 2020-04-01 Tianhong Li , Jianguo Li , Zhuang Liu , Changshui Zhang

Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc.…

Machine Learning · Computer Science 2021-01-13 Yang Fan , Yingce Xia , Lijun Wu , Shufang Xie , Weiqing Liu , Jiang Bian , Tao Qin , Xiang-Yang Li

We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transformer encoders). Our proposed approach first trains BERT with…

Machine Learning · Computer Science 2021-10-11 Shuo Yang , Le Hou , Xiaodan Song , Qiang Liu , Denny Zhou

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation process often leads to…

Machine Learning · Statistics 2021-04-21 Tri Dao , Govinda M Kamath , Vasilis Syrgkanis , Lester Mackey

This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…

Computation and Language · Computer Science 2024-12-30 Shuo Wang , Chihang Wang , Jia Gao , Zhen Qi , Hongye Zheng , Xiaoxuan Liao

Knowledge distillation, a widely used model compression technique, works on the basis of transferring knowledge from a cumbersome teacher model to a lightweight student model. The technique involves jointly optimizing the task specific and…

Machine Learning · Computer Science 2024-05-15 Shreyan Ganguly , Roshan Nayak , Rakshith Rao , Ujan Deb , Prathosh AP

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

Despite deep neural networks have demonstrated extraordinary power in various applications, their superior performances are at expense of high storage and computational costs. Consequently, the acceleration and compression of neural…

Computer Vision and Pattern Recognition · Computer Science 2017-12-20 Zehao Huang , Naiyan Wang

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT…

Computation and Language · Computer Science 2021-07-23 Haoli Bai , Wei Zhang , Lu Hou , Lifeng Shang , Jing Jin , Xin Jiang , Qun Liu , Michael Lyu , Irwin King