English
Related papers

Related papers: DAdEE: Unsupervised Domain Adaptation in Early Exi…

200 papers

We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to…

Machine Learning · Computer Science 2020-12-23 Jinyong Hou , Jeremiah D. Deng , Stephen Cranefield , Xuejie Ding

This paper presents a modular approach to accelerate inference in large language models (LLMs) by adding early exit heads at intermediate transformer layers. Each head is trained in a self-supervised manner to mimic the main model's…

Computation and Language · Computer Science 2026-02-13 Florian Valade

We propose a simple domain adaptation method for neural networks in a supervised setting. Supervised domain adaptation is a way of improving the generalization performance on the target domain by using the source domain dataset, assuming…

Computation and Language · Computer Science 2016-07-05 Yusuke Watanabe , Kazuma Hashimoto , Yoshimasa Tsuruoka

In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model…

Computation and Language · Computer Science 2020-10-23 Wangchunshu Zhou , Canwen Xu , Tao Ge , Julian McAuley , Ke Xu , Furu Wei

We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from…

Machine Learning · Statistics 2019-01-08 Jeroen Manders , Twan van Laarhoven , Elena Marchiori

Pre-trained language models (PLMs) demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain. Although continued pre-training on a large domain-specific corpus is effective, it is costly…

Computation and Language · Computer Science 2023-06-09 Shizhe Diao , Tianyang Xu , Ruijia Xu , Jiawei Wang , Tong Zhang

Unsupervised domain adaptation aims at learning a shared model for two related, but not identical, domains by leveraging supervision from a source domain to an unsupervised target domain. A number of effective domain adaptation approaches…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Jinming Cao , Oren Katzir , Peng Jiang , Dani Lischinski , Danny Cohen-Or , Changhe Tu , Yangyan Li

Pre-trained language models (PLMs) have achieved remarkable success on various natural language understanding tasks. Simple fine-tuning of PLMs, on the other hand, might be suboptimal for domain-specific tasks because they cannot possibly…

Computation and Language · Computer Science 2022-08-05 Minki Kang , Jinheon Baek , Sung Ju Hwang

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Machine Learning · Computer Science 2025-10-14 Jinyang Zhang , Yue Fang , Hongxin Ding , Weibin Liao , Muyang Ye , Xu Chu , Junfeng Zhao , Yasha Wang

Traditional machine learning assumes that training and test sets are derived from the same distribution; however, this assumption does not always hold in practical applications. This distribution disparity can lead to severe performance…

Machine Learning · Computer Science 2025-02-18 Ahmad Chaddad , Yihang Wu , Yuchen Jiang , Ahmed Bouridane , Christian Desrosiers

Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily on manual trial-and-error processes, incur significant…

Machine Learning · Computer Science 2026-03-10 Sidharth Sinha , Anson Bastos , Xuchao Zhang , Akshay Nambi , Chetan Bansal , Saravan Rajmohan

A pre-trained language model, BERT, has brought significant performance improvements across a range of natural language processing tasks. Since the model is trained on a large corpus of diverse topics, it shows robust performance for domain…

Computation and Language · Computer Science 2020-10-26 Minho Ryu , Kichun Lee

Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Ziyue Li , Kan Ren , Xinyang Jiang , Bo Li , Haipeng Zhang , Dongsheng Li

Entity Matching (EM) involves identifying different data representations referring to the same entity from multiple data sources and is typically formulated as a binary classification problem. It is a challenging problem in data integration…

Computation and Language · Computer Science 2023-05-31 John Bosco Mugeni , Steven Lynden , Toshiyuki Amagasa , Akiyoshi Matono

Due to domain bias, directly deploying a deep person re-identification (re-ID) model trained on one dataset often achieves considerably poor accuracy on another dataset. In this paper, we propose an Adaptive Exploration (AE) method to…

Computer Vision and Pattern Recognition · Computer Science 2020-04-13 Yuhang Ding , Hehe Fan , Mingliang Xu , Yi Yang

In Large Language Model (LLM) inference, early-exit refers to stopping computation at an intermediate layer once the prediction is sufficiently confident, thereby reducing latency and cost. However, recent LLMs adopt improved pretraining…

Computation and Language · Computer Science 2026-03-26 Rui Wei , Rui Du , Hanfei Yu , Devesh Tiwari , Jian Li , Zhaozhuo Xu , Hao Wang

Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved significant progress in addressing this issue via learning…

Machine Learning · Computer Science 2023-09-27 Yulong Zhang , Shuhao Chen , Weisen Jiang , Yu Zhang , Jiangang Lu , James T. Kwok

Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce…

Computation and Language · Computer Science 2025-12-16 Sangmin Bae

Dense retrieval approaches can overcome the lexical gap and lead to significantly improved search results. However, they require large amounts of training data which is not available for most domains. As shown in previous work (Thakur et…

Computation and Language · Computer Science 2022-04-26 Kexin Wang , Nandan Thakur , Nils Reimers , Iryna Gurevych

Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model. In this paper, we empirically analyze the working mechanism of…

Computation and Language · Computer Science 2021-09-06 Lei Li , Yankai Lin , Deli Chen , Shuhuai Ren , Peng Li , Jie Zhou , Xu Sun
‹ Prev 1 4 5 6 7 8 10 Next ›