English
Related papers

Related papers: Domain Pre-training Impact on Representations

200 papers

Learning effective representations in image-based environments is crucial for sample efficient Reinforcement Learning (RL). Unfortunately, in RL, representation learning is confounded with the exploratory experience of the agent -- learning…

Machine Learning · Computer Science 2021-07-21 Denis Yarats , Rob Fergus , Alessandro Lazaric , Lerrel Pinto

Many Natural Language Processing applications nowadays rely on pre-trained word representations estimated from large text corpora such as news collections, Wikipedia and Web Crawl. In this paper, we show how to train high-quality word…

Computation and Language · Computer Science 2017-12-29 Tomas Mikolov , Edouard Grave , Piotr Bojanowski , Christian Puhrsch , Armand Joulin

We focus on multi-turn response selection in a retrieval-based dialog system. In this paper, we utilize the powerful pre-trained language model Bi-directional Encoder Representations from Transformer (BERT) for a multi-turn dialog system…

Computation and Language · Computer Science 2020-07-28 Taesun Whang , Dongyub Lee , Chanhee Lee , Kisu Yang , Dongsuk Oh , HeuiSeok Lim

Most machine learning theory and practice is concerned with learning a single task. In this thesis it is argued that in general there is insufficient information in a single task for a learner to generalise well and that what is required…

Machine Learning · Computer Science 2019-11-25 Jonathan Baxter

Multilingual pretraining and fine-tuning have remarkably succeeded in various natural language processing tasks. Transferring representations from one language to another is especially crucial for cross-lingual learning. One can expect…

Computation and Language · Computer Science 2024-03-26 Shaoxiong Ji , Timothee Mickus , Vincent Segonne , Jörg Tiedemann

Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training is to learn text representations that are useful for…

Computation and Language · Computer Science 2020-04-14 Shangwen Lv , Yuechen Wang , Daya Guo , Duyu Tang , Nan Duan , Fuqing Zhu , Ming Gong , Linjun Shou , Ryan Ma , Daxin Jiang , Guihong Cao , Ming Zhou , Songlin Hu

This work analyses the impact of self-supervised pre-training on document images in the context of document image classification. While previous approaches explore the effect of self-supervision on natural images, we show that patch-based…

Computer Vision and Pattern Recognition · Computer Science 2020-05-28 Adrian Cosma , Mihai Ghidoveanu , Michael Panaitescu-Liess , Marius Popescu

Transfer learning aims to leverage models pre-trained on source data to efficiently adapt to target setting, where only limited data are available for model fine-tuning. Recent works empirically demonstrate that adversarial training in the…

Machine Learning · Computer Science 2021-06-21 Zhun Deng , Linjun Zhang , Kailas Vodrahalli , Kenji Kawaguchi , James Zou

Foundation models in healthcare have largely adopted self supervised pretraining objectives inherited from natural language processing and computer vision, emphasizing reconstruction and large scale representation learning prior to…

Machine Learning · Computer Science 2026-03-24 Yang Zhang , Li Fan , Samuel Lawrence , Shi Li

Transfer learning is widely used to adapt large pretrained models to new tasks with only a small amount of new data. However, a challenge persists -- the features from the original task often do not fully cover what is needed for unseen…

Machine Learning · Computer Science 2026-02-10 Xingyu Alice Yang , Jianyu Zhang , Léon Bottou

Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models. Existing literature, e.g., \cite{kim2020adversarial}, empirically observe that the downstream tasks…

Machine Learning · Computer Science 2024-01-30 Yue Xing , Xiaofeng Lin , Qifan Song , Yi Xu , Belinda Zeng , Guang Cheng

Many recent studies on large-scale language models have reported successful in-context zero- and few-shot learning ability. However, the in-depth analysis of when in-context learning occurs is still lacking. For example, it is unknown how…

Computation and Language · Computer Science 2022-05-10 Seongjin Shin , Sang-Woo Lee , Hwijeen Ahn , Sungdong Kim , HyoungSeok Kim , Boseop Kim , Kyunghyun Cho , Gichang Lee , Woomyoung Park , Jung-Woo Ha , Nako Sung

Pretraining Neural Language Models (NLMs) over a large corpus involves chunking the text into training examples, which are contiguous text segments of sizes processable by the neural architecture. We highlight a bias introduced by this…

Computation and Language · Computer Science 2022-03-22 Yoav Levine , Noam Wies , Daniel Jannai , Dan Navon , Yedid Hoshen , Amnon Shashua

Recommender systems aim to provide item recommendations for users, and are usually faced with data sparsity problem (e.g., cold start) in real-world scenarios. Recently pre-trained models have shown their effectiveness in knowledge transfer…

Information Retrieval · Computer Science 2020-09-22 Zheni Zeng , Chaojun Xiao , Yuan Yao , Ruobing Xie , Zhiyuan Liu , Fen Lin , Leyu Lin , Maosong Sun

It is generally thought that transformer-based large language models benefit from pre-training by learning generic linguistic knowledge that can be focused on a specific task during fine-tuning. However, we propose that much of the benefit…

Computation and Language · Computer Science 2024-06-19 Anna C. Marbut , John W. Chandler , Travis J. Wheeler

Transformers have theoretical limitations in modeling certain sequence-to-sequence tasks, yet it remains largely unclear if these limitations play a role in large-scale pretrained LLMs, or whether LLMs might effectively overcome these…

Machine Learning · Computer Science 2025-10-24 Mayank Jobanputra , Yana Veitsman , Yash Sarrof , Aleksandra Bakalova , Vera Demberg , Ellie Pavlick , Michael Hahn

In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain. Specifically, we evaluate the effectiveness of Masked Autoencoding as a pretraining scheme, and explore Momentum…

Computer Vision and Pattern Recognition · Computer Science 2024-04-16 Ioannis Romanelis , Vlassis Fotis , Konstantinos Moustakas , Adrian Munteanu

While conditional diffusion models have achieved remarkable success in various applications, they require abundant data to train from scratch, which is often infeasible in practice. To address this issue, transfer learning has emerged as an…

Machine Learning · Computer Science 2025-10-28 Ziheng Cheng , Tianyu Xie , Shiyue Zhang , Cheng Zhang

Pre-training has exhibited notable benefits to downstream tasks by boosting accuracy and speeding up convergence, but the exact reasons for these benefits still remain unclear. To this end, we propose to quantitatively and explicitly…

Machine Learning · Computer Science 2024-10-14 Xin Jiang , Xu Cheng , Zechao Li

In this work we study how explicit world-modeling objectives affect the internal representations and downstream capability of Transformers across different training stages. We use a controlled 2x2x2 Rubik's Cube and ask: (1) how does…

Machine Learning · Computer Science 2025-12-04 Prakhar Gupta , Henry Conklin , Sarah-Jane Leslie , Andrew Lee