English
Related papers

Related papers: Contrastive Distillation on Intermediate Represent…

200 papers

Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and matching tasks. In this paper, we integrate contrastive…

Computation and Language · Computer Science 2023-05-02 Weiting Tan , Kevin Heffernan , Holger Schwenk , Philipp Koehn

Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data…

Computer Vision and Pattern Recognition · Computer Science 2023-05-02 Muzhou Yu , Sia Huat Tan , Kailu Wu , Runpei Dong , Linfeng Zhang , Kaisheng Ma

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-time applications.…

Computation and Language · Computer Science 2022-11-03 Haojie Pan , Chengyu Wang , Minghui Qiu , Yichang Zhang , Yaliang Li , Jun Huang

In this paper, we propose that small models may not need to absorb the cost of pre-training to reap its benefits. Instead, they can capitalize on the astonishing results achieved by modern, enormous models to a surprising degree. We observe…

Machine Learning · Computer Science 2024-05-06 Sean Farhat , Deming Chen

Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strategy. Our approach…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 David E. Hernandez , Jose Chang , Torbjörn E. M. Nordling

The smaller memory bandwidth in smart devices prompts development of smaller Automatic Speech Recognition (ASR) models. To obtain a smaller model, one can employ the model compression techniques. Knowledge distillation (KD) is a popular…

Sound · Computer Science 2022-10-04 Jash Rathod , Nauman Dawalatabad , Shatrughan Singh , Dhananjaya Gowda

Since the advent of knowledge distillation, much research has focused on how the soft labels generated by the teacher model can be utilized effectively. Existing studies points out that the implicit knowledge within soft labels originates…

Machine Learning · Computer Science 2025-09-29 Hua Yuan , Ning Xu , Xin Geng , Yong Rui

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

We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur…

Computation and Language · Computer Science 2024-08-26 Phuc Phan , Hieu Tran , Long Phan

The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Alex Andonian , Shixing Chen , Raffay Hamid

Model inversion, whose goal is to recover training data from a pre-trained model, has been recently proved feasible. However, existing inversion methods usually suffer from the mode collapse problem, where the synthesized instances are…

Artificial Intelligence · Computer Science 2021-05-19 Gongfan Fang , Jie Song , Xinchao Wang , Chengchao Shen , Xingen Wang , Mingli Song

Pre-trained language models (PLMs) achieve great success in NLP. However, their huge model sizes hinder their applications in many practical systems. Knowledge distillation is a popular technique to compress PLMs, which learns a small…

Computation and Language · Computer Science 2021-06-03 Chuhan Wu , Fangzhao Wu , Yongfeng Huang

With growing attention to tabular data these days, the attempt to apply a synthetic table to various tasks has been expanded toward various scenarios. Owing to the recent advances in generative modeling, fake data generated by tabular data…

Machine Learning · Computer Science 2023-09-22 Chaejeong Lee , Jayoung Kim , Noseong Park

Distillation efforts have led to language models that are more compact and efficient without serious drops in performance. The standard approach to distillation trains a student model against two objectives: a task-specific objective (e.g.,…

Computation and Language · Computer Science 2022-06-07 Zhengxuan Wu , Atticus Geiger , Josh Rozner , Elisa Kreiss , Hanson Lu , Thomas Icard , Christopher Potts , Noah D. Goodman

Pre-trained Language Models (PLMs) have been successful for a wide range of natural language processing (NLP) tasks. The state-of-the-art of PLMs, however, are extremely large to be used on edge devices. As a result, the topic of model…

Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text…

Computer Vision and Pattern Recognition · Computer Science 2022-08-25 Yixuan Wei , Han Hu , Zhenda Xie , Zheng Zhang , Yue Cao , Jianmin Bao , Dong Chen , Baining Guo

In this paper, we introduce InDistill, a method that serves as a warmup stage for enhancing Knowledge Distillation (KD) effectiveness. InDistill focuses on transferring critical information flow paths from a heavyweight teacher to a…

Computer Vision and Pattern Recognition · Computer Science 2025-01-23 Ioannis Sarridis , Christos Koutlis , Giorgos Kordopatis-Zilos , Ioannis Kompatsiaris , Symeon Papadopoulos

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

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

Machine Learning · Computer Science 2026-01-12 Pattarawat Chormai , Ali Hashemi , Klaus-Robert Müller , Grégoire Montavon

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…

Computation and Language · Computer Science 2021-02-09 Sanqiang Zhao , Raghav Gupta , Yang Song , Denny Zhou