English
Related papers

Related papers: Self-Regulated Data-Free Knowledge Amalgamation fo…

200 papers

AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns…

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

Computation and Language · Computer Science 2020-05-11 Xing Wu , Yibing Liu , Xiangyang Zhou , Dianhai Yu

Traditional knowledge distillation transfers "dark knowledge" of a pre-trained teacher network to a student network, and ignores the knowledge in the training process of the teacher, which we call teacher's experience. However, in realistic…

Computer Vision and Pattern Recognition · Computer Science 2022-02-28 Chaofei Wang , Shaowei Zhang , Shiji Song , Gao Huang

Knowledge Distillation (KD) aims to transfer knowledge in a teacher-student framework, by providing the predictions of the teacher network to the student network in the training stage to help the student network generalize better. It can…

Computer Vision and Pattern Recognition · Computer Science 2019-09-25 SeongUk Park , Nojun Kwak

Multi-source domain adaptation has been intensively studied. The distribution shift in features inherent to specific domains causes the negative transfer problem, degrading a model's generality to unseen tasks. In Federated Learning (FL),…

Machine Learning · Computer Science 2022-10-18 Yuwei Sun , Ng Chong , Hideya Ochiai

Crossmodal knowledge distillation (KD) aims to enhance a unimodal student using a multimodal teacher model. In particular, when the teacher's modalities include the student's, additional complementary information can be exploited to improve…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Chenqi Guo , Mengshuo Rong , Qianli Feng , Rongfan Feng , Yinglong Ma

Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing DFML work can only meta-learn from (i) white-box and (ii)…

Machine Learning · Computer Science 2025-02-18 Zixuan Hu , Li Shen , Zhenyi Wang , Baoyuan Wu , Chun Yuan , Dacheng Tao

Data-free knowledge distillation transfers knowledge by recovering training data from a pre-trained model. Despite the recent success of seeking global data diversity, the diversity within each class and the similarity among different…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Yingping Liang , Ying Fu

It is well known that a speech recognition system that combines multiple acoustic models trained on the same data significantly outperforms a single-model system. Unfortunately, real time speech recognition using a whole ensemble of models…

Computation and Language · Computer Science 2019-06-27 Zhenchuan Yang , Chun Zhang , Weibin Zhang , Jianxiu Jin , Dongpeng Chen

Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data. However, most of the existing works on FL…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Donald Shenaj , Eros Fanì , Marco Toldo , Debora Caldarola , Antonio Tavera , Umberto Michieli , Marco Ciccone , Pietro Zanuttigh , Barbara Caputo

Recent work suggests that interpolating between the weights of two specialized language models can transfer knowledge between tasks in a way that multi-task learning cannot. However, very few have explored interpolation between more than…

Computation and Language · Computer Science 2023-07-27 Dean Ninalga

The model reduction problem that eases the computation costs and latency of complex deep learning architectures has received an increasing number of investigations owing to its importance in model deployment. One promising method is…

Machine Learning · Computer Science 2018-12-04 Wei-Chun Chen , Chia-Che Chang , Chien-Yu Lu , Che-Rung Lee

Is it possible to design an universal API for federated learning using which an ad-hoc group of data-holders (agents) collaborate with each other and perform federated learning? Such an API would necessarily need to be model-agnostic i.e.…

Machine Learning · Computer Science 2022-05-12 Andrei Afonin , Sai Praneeth Karimireddy

Federated learning enables joint training of machine learning models from distributed clients without sharing their local data. One key challenge in federated learning is to handle non-identically distributed data across the clients, which…

Machine Learning · Computer Science 2023-12-25 Tiejin Chen , Yuanpu Cao , Yujia Wang , Cho-Jui Hsieh , Jinghui Chen

Purpose: Advances in surgical phase recognition are generally led by training deeper networks. Rather than going further with a more complex solution, we believe that current models can be exploited better. We propose a self-knowledge…

Image and Video Processing · Electrical Eng. & Systems 2023-06-16 Jinglu Zhang , Santiago Barbarisi , Abdolrahim Kadkhodamohammadi , Danail Stoyanov , Imanol Luengo

Recently, deep learning has been adopted to the glaucoma classification task with performance comparable to that of human experts. However, a well trained deep learning model demands a large quantity of properly labeled data, which is…

Computer Vision and Pattern Recognition · Computer Science 2020-07-23 Junde Wu , Shuang Yu , Wenting Chen , Kai Ma , Rao Fu , Hanruo Liu , Xiaoguang Di , Yefeng Zheng

Deep network compression has been achieved notable progress via knowledge distillation, where a teacher-student learning manner is adopted by using predetermined loss. Recently, more focuses have been transferred to employ the adversarial…

Machine Learning · Computer Science 2019-04-26 Shu Changyong , Li Peng , Xie Yuan , Qu Yanyun , Dai Longquan , Ma Lizhuang

Knowledge distillation (KD) is a successful approach for deep neural network acceleration, with which a compact network (student) is trained by mimicking the softmax output of a pre-trained high-capacity network (teacher). In tradition, KD…

Machine Learning · Computer Science 2021-06-08 Zi Wang

Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple…

Computers and Society · Computer Science 2022-01-19 Sujanya Suresh , Savitha Ramasamy , P. N. Suganthan , Cheryl Sze Yin Wong

Federated Learning (FL) is a distributed machine learning paradigm which coordinates multiple clients to collaboratively train a global model via a central server. Sequential Federated Learning (SFL) is a newly-emerging FL training…

Machine Learning · Computer Science 2025-07-14 Haotian Xu , Jinrui Zhou , Xichong Zhang , Mingjun Xiao , He Sun , Yin Xu