English
Related papers

Related papers: A general framework for ensemble distribution dist…

200 papers

Knowledge distillation describes a method for training a student network to perform better by learning from a stronger teacher network. Translating a sentence with an Neural Machine Translation (NMT) engine is time expensive and having a…

Computation and Language · Computer Science 2017-08-09 Markus Freitag , Yaser Al-Onaizan , Baskaran Sankaran

Ensembles improve prediction performance and allow uncertainty quantification by aggregating predictions from multiple models. In deep ensembling, the individual models are usually black box neural networks, or recently, partially…

Machine Learning · Statistics 2022-05-26 Lucas Kook , Andrea Götschi , Philipp FM Baumann , Torsten Hothorn , Beate Sick

Many natural language processing tasks can be modeled into structured prediction and solved as a search problem. In this paper, we distill an ensemble of multiple models trained with different initialization into a single model. In addition…

Computation and Language · Computer Science 2018-05-30 Yijia Liu , Wanxiang Che , Huaipeng Zhao , Bing Qin , Ting Liu

In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions. To this end, we propose an ensemble of Normalizing Flows (NF), which are…

Machine Learning · Computer Science 2023-10-05 Lucas Berry , David Meger

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…

Machine Learning · Computer Science 2021-03-26 Zhenyan Hou , Wenxuan Fan

Considering uncertainty estimation of modern neural networks (NNs) is one of the most important steps towards deploying machine learning systems to meaningful real-world applications such as in medicine, finance or autonomous systems. At…

Machine Learning · Computer Science 2022-05-20 Martin Ferianc , Miguel Rodrigues

We study the problem of progressive ensemble distillation: Given a large, pretrained teacher model $g$, we seek to decompose the model into smaller, low-inference cost student models $f_i$, such that progressively evaluating additional…

Machine Learning · Computer Science 2023-11-10 Don Kurian Dennis , Abhishek Shetty , Anish Sevekari , Kazuhito Koishida , Virginia Smith

Neural networks can learn spurious correlations in the data, often leading to performance degradation for underrepresented subgroups. Studies have demonstrated that the disparity is amplified when knowledge is distilled from a complex…

Machine Learning · Computer Science 2025-11-11 Patrik Kenfack , Ulrich Aïvodji , Samira Ebrahimi Kahou

In this paper, we propose Neural Spectrum Decomposition, a generic decomposition framework for dataset distillation. Unlike previous methods, we consider the entire dataset as a high-dimensional observation that is low-rank across all…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Shaolei Yang , Shen Cheng , Mingbo Hong , Haoqiang Fan , Xing Wei , Shuaicheng Liu

Ensembles of machine learning models yield improved system performance as well as robust and interpretable uncertainty estimates; however, their inference costs may often be prohibitively high. \emph{Ensemble Distribution Distillation} is…

Machine Learning · Computer Science 2021-05-17 Max Ryabinin , Andrey Malinin , Mark Gales

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In…

Machine Learning · Computer Science 2020-04-08 Sukmin Yun , Jongjin Park , Kimin Lee , Jinwoo Shin

Deep learning has contributed greatly to many successes in artificial intelligence in recent years. Today, it is possible to train models that have thousands of layers and hundreds of billions of parameters. Large-scale deep models have…

Machine Learning · Computer Science 2023-02-15 Konrad Zuchniak

We propose an efficient way to output better calibrated uncertainty scores from neural networks. The Distilled Dropout Network (DDN) makes standard (non-Bayesian) neural networks more introspective by adding a new training loss which…

Computer Vision and Pattern Recognition · Computer Science 2018-09-28 Corina Gurau , Alex Bewley , Ingmar Posner

Ensembles of neural networks (NNs) have long been used to estimate predictive uncertainty; a small number of NNs are trained from different initialisations and sometimes on differing versions of the dataset. The variance of the ensemble's…

Machine Learning · Computer Science 2018-11-30 Tim Pearce , Mohamed Zaki , Andy Neely

Graph Neural Networks (GNNs) have shown remarkable performance in the healthcare domain. However, what remained challenging is quantifying the predictive uncertainty of GNNs, which is an important aspect of trustworthiness in clinical…

Machine Learning · Computer Science 2025-08-28 Hirad Daneshvar , Reza Samavi

Domain generalization is the task of learning models that generalize to unseen target domains. We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED), that learns domain-invariant…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Kyungmoon Lee , Sungyeon Kim , Suha Kwak

Deep ensembles deliver state-of-the-art, reliable uncertainty quantification, but their heavy computational and memory requirements hinder their practical deployments to real applications such as on-device AI. Knowledge distillation…

Machine Learning · Computer Science 2025-10-27 Sehyun Park , Jongjin Lee , Yunseop Shin , Ilsang Ohn , Yongdai Kim

Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. \emph{Deep ensembles}, a state-of-the-art method for uncertainty…

Machine Learning · Computer Science 2022-02-23 Sheheryar Zaidi , Arber Zela , Thomas Elsken , Chris Holmes , Frank Hutter , Yee Whye Teh

In this paper, we present a general framework for distilling expectations with respect to the Bayesian posterior distribution of a deep neural network classifier, extending prior work on the Bayesian Dark Knowledge framework. The proposed…

Machine Learning · Computer Science 2020-05-19 Meet P. Vadera , Brian Jalaian , Benjamin M. Marlin

This paper introduces a distillation framework for an ensemble of entropy-optimal Sparse Probabilistic Approximation (eSPA) models, trained exclusively on satellite-era observational and reanalysis data to predict ENSO phase up to 24 months…

Computational Physics · Physics 2026-02-20 Michael Groom , Davide Bassetti , Illia Horenko , Terence J. O'Kane