English
Related papers

Related papers: Enhancing Masked Time-Series Modeling via Dropping…

200 papers

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

Shapelet-based algorithms are widely used for time series classification because of their ease of interpretation, but they are currently outperformed by recent state-of-the-art approaches. We present a new formulation of time series…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Antoine Guillaume , Christel Vrain , Elloumi Wael

The ability to adapt to changing environments and settings is essential for robots acting in dynamic and unstructured environments or working alongside humans with varied abilities or preferences. This work introduces an extremely simple…

Robotics · Computer Science 2022-10-31 Pamela Carreno-Medrano , Dana Kulić , Michael Burke

Attentive Neural Process (ANP) improves the fitting ability of Neural Process (NP) and improves its prediction accuracy, but the higher time complexity of the model imposes a limitation on the length of the input sequence. Inspired by…

Computer Vision and Pattern Recognition · Computer Science 2022-02-07 Xiaohan Yu , Shaochen Mao

Distributed multi-party learning provides an effective approach for training a joint model with scattered data under legal and practical constraints. However, due to the quagmire of a skewed distribution of data labels across participants…

Machine Learning · Computer Science 2021-11-01 Maoguo Gong , Yuan Gao , Yue Wu , A. K. Qin

The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation regimes. We introduce a novel sampling algorithm that works…

In recent years, the application of transformer-based models in time-series forecasting has received significant attention. While often demonstrating promising results, the transformer architecture encounters challenges in fully exploiting…

Machine Learning · Computer Science 2025-02-12 Artyom Stitsyuk , Jaesik Choi

Residual connections are one of the most important components in neural network architectures for mitigating the vanishing gradient problem and facilitating the training of much deeper networks. One possible explanation for how residual…

Machine Learning · Computer Science 2024-11-15 Sejik Park

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Computation and Language · Computer Science 2022-03-25 Le Hou , Richard Yuanzhe Pang , Tianyi Zhou , Yuexin Wu , Xinying Song , Xiaodan Song , Denny Zhou

Originally, dropout was seen as a breakthrough regularization technique that reduced overfitting and improved performance in almost all applications of deep learning by reducing overfitting. Yet, single-epoch pretraining tasks common to…

Computation and Language · Computer Science 2025-06-02 Houjun Liu , John Bauer , Christopher D. Manning

The inherently diverse and uncertain nature of trajectories presents a formidable challenge in accurately modeling them. Motion prediction systems must effectively learn spatial and temporal information from the past to forecast the future…

Robotics · Computer Science 2023-11-28 Pranav Singh Chib , Pravendra Singh

Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes…

Machine Learning · Computer Science 2018-12-11 Rohit Keshari , Richa Singh , Mayank Vatsa

Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and layer dropping (Reddi et al, 2023; Zhang & He, 2020), have…

Computation and Language · Computer Science 2024-10-15 Abhishek Panigrahi , Nikunj Saunshi , Kaifeng Lyu , Sobhan Miryoosefi , Sashank Reddi , Satyen Kale , Sanjiv Kumar

Attention-based architectures have achieved superior performance in multivariate time series forecasting but are computationally expensive. Techniques such as patching and adaptive masking have been developed to reduce their sizes and…

Machine Learning · Computer Science 2025-05-14 Suhan Guo , Jiahong Deng , Mengjun Yi , Furao Shen , Jian Zhao

Existing approaches for learning representations of time-series keep the temporal arrangement of the time-steps intact with the presumption that the original order is the most optimal for learning. However, non-adjacent sections of…

Machine Learning · Computer Science 2024-10-31 Shivam Grover , Amin Jalali , Ali Etemad

Dropout has been demonstrated as a simple and effective module to not only regularize the training process of deep neural networks, but also provide the uncertainty estimation for prediction. However, the quality of uncertainty estimation…

Machine Learning · Computer Science 2021-03-09 Xinjie Fan , Shujian Zhang , Korawat Tanwisuth , Xiaoning Qian , Mingyuan Zhou

Training diffusion models is always a computation-intensive task. In this paper, we introduce a novel speed-up method for diffusion model training, called, which is based on a closer look at time steps. Our key findings are: i) Time steps…

Machine Learning · Computer Science 2025-03-26 Kai Wang , Mingjia Shi , Yukun Zhou , Zekai Li , Zhihang Yuan , Yuzhang Shang , Xiaojiang Peng , Hanwang Zhang , Yang You

Masked diffusion models (MDMs) have emerged as a promising alternative to autoregressive models for language modeling, yet the effective design of transformer architectures for MDMs remains underexplored. In this paper, we show that…

Machine Learning · Computer Science 2026-05-26 Sanghyun Lee , Chunsan Hong , Seungryong Kim , Jonghyun Lee , Jongho Park , Dongmin Park

Large-scale self-supervised pre-training Transformer architecture have significantly boosted the performance for various tasks in natural language processing (NLP) and computer vision (CV). However, there is a lack of researches on…

Machine Learning · Computer Science 2022-10-06 Peiwang Tang , Xianchao Zhang

As the field of deep learning steadily transitions from the realm of academic research to practical application, the significance of self-supervised pretraining methods has become increasingly prominent. These methods, particularly in the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-23 Toni Albert , Bjoern Eskofier , Dario Zanca