English
Related papers

Related papers: Sampling and Loss Weights in Multi-Domain Training

200 papers

Estimating causal effects from observational data is a central problem in many domains. A general approach is to balance covariates with weights such that the distribution of the data mimics randomization. We present generalized balancing…

Machine Learning · Statistics 2023-10-02 Yoshiaki Kitazawa

Neural networks have been successfully used for classification tasks in a rapidly growing number of practical applications. Despite their popularity and widespread use, there are still many aspects of training and classification that are…

Machine Learning · Computer Science 2016-05-03 Ewout van den Berg

Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they…

Machine Learning · Computer Science 2024-07-03 Mohamed Elsayed , Qingfeng Lan , Clare Lyle , A. Rupam Mahmood

Large foundation models are typically trained on data from multiple domains, with the data mixture--the proportion of each domain used--playing a critical role in model performance. The standard approach to selecting this mixture relies on…

Machine Learning · Computer Science 2025-10-03 Mustafa Shukor , Louis Bethune , Dan Busbridge , David Grangier , Enrico Fini , Alaaeldin El-Nouby , Pierre Ablin

Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices contributes to the…

Machine Learning · Computer Science 2025-01-27 Arash Behboodi , Gabriele Cesa

Training a deep neural model for semantic segmentation requires collecting a large amount of pixel-level labeled data. To alleviate the data scarcity problem presented in the real world, one could utilize synthetic data whose label is easy…

Computer Vision and Pattern Recognition · Computer Science 2021-11-10 Yiren Jian , Chongyang Gao

Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple loss terms act as hyperparameters. Tuning these weights with random search or Bayesian…

Machine Learning · Computer Science 2026-05-11 Ivan Karpukhin , Andrey Savchenko

Re-using trained neural network models is a common strategy to reduce training cost and transfer knowledge. Weight space learning - using the weights of trained models as data modality - is a promising new field to re-use populations of…

Machine Learning · Computer Science 2025-04-15 Damian Falk , Konstantin Schürholt , Damian Borth

A distribution shift between the training and test data can severely harm performance of machine learning models. Importance weighting addresses this issue by assigning different weights to data points during training. We argue that…

Machine Learning · Statistics 2025-11-17 Floris Holstege , Bram Wouters , Noud van Giersbergen , Cees Diks

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled importance sampling scheme that focuses computation on…

Machine Learning · Computer Science 2019-10-29 Angelos Katharopoulos , François Fleuret

The performance of deep neural networks is enhanced by ensemble methods, which average the output of several models. However, this comes at an increased cost at inference. Weight averaging methods aim at balancing the generalization of…

Machine Learning · Computer Science 2024-05-29 Louis Fournier , Adel Nabli , Masih Aminbeidokhti , Marco Pedersoli , Eugene Belilovsky , Edouard Oyallon

The success of large neural networks is crucially determined by the availability of data. It has been observed that training only on a small amount of public data, or privately on the abundant private data can lead to undesirable…

Machine Learning · Computer Science 2023-10-03 Ruixuan Liu , Zhiqi Bu , Yu-xiang Wang , Sheng Zha , George Karypis

Domain shifts are ubiquitous in machine learning, and can substantially degrade a model's performance when deployed to real-world data. To address this, distribution alignment methods aim to learn feature representations which are invariant…

Machine Learning · Computer Science 2024-10-08 Andrea Napoli , Paul White

Modern deep neural networks rely heavily on massive model weights and training samples, incurring substantial computational costs. Weight pruning and coreset selection are two emerging paradigms proposed to improve computational efficiency.…

Machine Learning · Computer Science 2025-11-18 Weilin Wan , Fan Yi , Weizhong Zhang , Quan Zhou , Cheng Jin

This paper presents an empirical study on the weights of neural networks, where we interpret each model as a point in a high-dimensional space -- the neural weight space. To explore the complex structure of this space, we sample from a…

Computer Vision and Pattern Recognition · Computer Science 2020-02-14 Gabriel Eilertsen , Daniel Jönsson , Timo Ropinski , Jonas Unger , Anders Ynnerman

Open-domain conversational systems are assumed to generate equally good responses on multiple domains. Previous work achieved good performance on the single corpus, but training and evaluating on multiple corpora from different domains are…

Computation and Language · Computer Science 2022-05-06 Yujie Xing , Jinglun Cai , Nils Barlaug , Peng Liu , Jon Atle Gulla

Text classification is a very classic NLP task, but it has two prominent shortcomings: On the one hand, text classification is deeply domain-dependent. That is, a classifier trained on the corpus of one domain may not perform so well in…

Computation and Language · Computer Science 2022-10-28 Zilin Yuan , Yinghui Li , Yangning Li , Rui Xie , Wei Wu , Hai-Tao Zheng

We consider the problem of learning a model from multiple heterogeneous sources with the goal of performing well on a new target distribution. The goal of learner is to mix these data sources in a target-distribution aware way and…

Machine Learning · Computer Science 2023-11-14 Yuyang Deng , Ilja Kuzborskij , Mehrdad Mahdavi

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the…

Machine Learning · Computer Science 2021-03-26 Gianni Franchi , Andrei Bursuc , Emanuel Aldea , Severine Dubuisson , Isabelle Bloch

We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc…

Computer Vision and Pattern Recognition · Computer Science 2018-05-23 Xiaojie Jin , Yingzhen Yang , Ning Xu , Jianchao Yang , Nebojsa Jojic , Jiashi Feng , Shuicheng Yan