English
Related papers

Related papers: Domain Mixture Design via Log-Likelihood Differenc…

200 papers

The mixture proportions of pretraining data domains (e.g., Wikipedia, books, web text) greatly affect language model (LM) performance. In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a…

Computation and Language · Computer Science 2023-11-22 Sang Michael Xie , Hieu Pham , Xuanyi Dong , Nan Du , Hanxiao Liu , Yifeng Lu , Percy Liang , Quoc V. Le , Tengyu Ma , Adams Wei Yu

A recent trend in Natural Language Processing is the exponential growth in Language Model (LM) size, which prevents research groups without a necessary hardware infrastructure from participating in the development process. This study…

Computation and Language · Computer Science 2023-01-31 Jan Philip Wahle

In the problem of domain generalization (DG), there are labeled training data sets from several related prediction problems, and the goal is to make accurate predictions on future unlabeled data sets that are not known to the learner. This…

Machine Learning · Statistics 2021-01-08 Gilles Blanchard , Aniket Anand Deshmukh , Urun Dogan , Gyemin Lee , Clayton Scott

Distribution alignment has many applications in deep learning, including domain adaptation and unsupervised image-to-image translation. Most prior work on unsupervised distribution alignment relies either on minimizing simple non-parametric…

Machine Learning · Computer Science 2020-10-27 Ben Usman , Avneesh Sud , Nick Dufour , Kate Saenko

Continual pre-training on small-scale task-specific data is an effective method for improving large language models in new target fields, yet it risks catastrophic forgetting of their original capabilities. A common solution is to re-weight…

Machine Learning · Computer Science 2026-04-14 Kailai Yang , Xiao Liu , Lei Ji , Hao Li , Xiao Liang , Zhiwei Liu , Yeyun Gong , Peng Cheng , Mao Yang

Many multi-domain neural machine translation (NMT) models achieve knowledge transfer by enforcing one encoder to learn shared embedding across domains. However, this design lacks adaptation to individual domains. To overcome this…

Computation and Language · Computer Science 2021-02-15 Haoming Jiang , Chen Liang , Chong Wang , Tuo Zhao

Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks without retraining, the quality of these subnetworks is not…

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

The distribution shifts between training and test data typically undermine the performance of models. In recent years, lots of work pays attention to domain generalization (DG) where distribution shifts exist, and target data are unseen.…

Machine Learning · Computer Science 2024-01-05 Wang Lu , Jindong Wang , Yidong Wang , Xing Xie

When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-06 Han Zhu , Jiangjiang Zhao , Yuling Ren , Li Wang , Pengyuan Zhang

Motivated by the success of pre-trained language models such as BERT in a broad range of natural language processing (NLP) tasks, recent research efforts have been made for adapting these models for different application domains. Along this…

Computation and Language · Computer Science 2021-12-07 Denghui Zhang , Zixuan Yuan , Yanchi Liu , Hao Liu , Fuzhen Zhuang , Hui Xiong , Haifeng Chen

Domain shift refers to the well known problem that a model trained in one source domain performs poorly when applied to a target domain with different statistics. {Domain Generalization} (DG) techniques attempt to alleviate this issue by…

Machine Learning · Computer Science 2017-10-11 Da Li , Yongxin Yang , Yi-Zhe Song , Timothy M. Hospedales

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

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

Topic models are often used to identify human-interpretable topics to help make sense of large document collections. We use knowledge distillation to combine the best attributes of probabilistic topic models and pretrained transformers. Our…

Computation and Language · Computer Science 2020-10-07 Alexander Hoyle , Pranav Goel , Philip Resnik

A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce…

Computation and Language · Computer Science 2021-09-20 Geondo Park , Gyeongman Kim , Eunho Yang

Domain generalization (DG) is about training models that generalize well under domain shift. Previous research on DG has been conducted mostly in single-source or multi-source settings. In this paper, we consider a third, lesser-known…

Machine Learning · Computer Science 2024-06-13 Han Gao , Kaican Li , Weiyan Xie , Zhi Lin , Yongxiang Huang , Luning Wang , Caleb Chen Cao , Nevin L. Zhang

Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains. In a standard fine-tuning scheme, source and target problems are trained using the same architecture. Although capable of…

Computation and Language · Computer Science 2019-04-09 Sara Meftah , Youssef Tamaazousti , Nasredine Semmar , Hassane Essafi , Fatiha Sadat

Domain Generalization (DG) aims to generalize to arbitrary unseen domains. A promising approach to improve model generalization in DG is the identification of flat minima. One typical method for this task is SWAD, which involves averaging…

Computer Vision and Pattern Recognition · Computer Science 2023-09-13 Jian Zhang , Lei Qi , Yinghuan Shi , Yang Gao

Automated evaluation of open domain natural language generation (NLG) models remains a challenge and widely used metrics such as BLEU and Perplexity can be misleading in some cases. In our paper, we propose to evaluate natural language…

Computation and Language · Computer Science 2020-02-13 Wangchunshu Zhou , Ke Xu