paper-with-me

홈 › Papers

Enhancing Masked Time-Series Modeling via Dropping Patches

2024-12-19 · Tianyu Qiu, Yi Xie, Yun Xiong, Hao Niu, Xiaofeng Gao

This paper explores how to enhance existing masked time-series modeling by randomly dropping sub-sequence level patches of time series. On this basis, a simple yet effective method named DropPatch is proposed, which has two remarkable advantages: 1) It improves the pre-training efficiency by a square-level advantage; 2) It provides additional advantages for modeling in scenarios such as in-domain, cross-domain, few-shot learning and cold start. This paper conducts comprehensive experiments to verify the effectiveness of the method and analyze its internal mechanism. Empirically, DropPatch strengthens the attention mechanism, reduces information redundancy and serves as an efficient means of data augmentation. Theoretically, it is proved that DropPatch slows down the rate at which the Transformer representations collapse into the rank-1 linear subspace by randomly dropping patches, thus optimizing the quality of the learned representations

📄 PDF Abstract BibTeX arXiv:2412.15315

Code (1)

qityy/droppatch 공식 구현 pytorch

Tasks

Cross-Domain Few-Shotcross-domain few-shot learningData AugmentationFew-Shot LearningTime Series

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

2023-02-02 · NeurIPS 2023 11 · Jiaxiang Dong, Haixu Wu, Haoran Zhang, Li Zhang 외

Time series analysis is widely used in extensive areas. Recently, to reduce labeling expenses and benefit various tasks, self-supervised pre-training has attracted immense interest. One mainstream paradigm is masked mode…

Representation LearningTime SeriesTime Series Analysis

Explainable Time Series Anomaly Detection using Masked Latent Generative Modeling

2023-11-21 · Daesoo Lee, Sara Malacarne, Erlend Aune

We present a novel time series anomaly detection method that achieves excellent detection accuracy while offering a superior level of explainability. Our proposed method, TimeVQVAE-AD, leverages masked generative modelin…

Anomaly DetectionTime SeriesTime Series Anomaly DetectionTime Series Generation

TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders

2023-03-01 · Mingyue Cheng, Qi Liu, Zhiding Liu, Hao Zhang 외

Enhancing the expressive capacity of deep learning-based time series models with self-supervised pre-training has become ever-increasingly prevalent in time series classification. Even though numerous efforts have been d…

Time SeriesTime Series AnalysisTime Series Classification

Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer

2022-05-20 · Wenrui Zhang, Ling Yang, Shijia Geng, Shenda Hong

Unsupervised/self-supervised representation learning in time series is critical since labeled samples are usually scarce in real-world scenarios. Existing approaches mainly leverage the contrastive learning framework, wh…

Contrastive LearningRepresentation LearningTime SeriesTime Series Analysis

Learning to Embed Time Series Patches Independently

2023-12-27 · Seunghan Lee, Taeyoung Park, Kibok Lee

Masked time series modeling has recently gained much attention as a self-supervised representation learning strategy for time series. Inspired by masked image modeling in computer vision, recent works first patchify and …

Contrastive LearningRepresentation LearningTime SeriesTime Series Forecasting