paper-with-me

홈 › Papers

Multi-scale Transformer Pyramid Networks for Multivariate Time Series Forecasting

2023-08-23 · Yifan Zhang, Rui Wu, Sergiu M. Dascalu, Frederick C. Harris Jr

Multivariate Time Series (MTS) forecasting involves modeling temporal dependencies within historical records. Transformers have demonstrated remarkable performance in MTS forecasting due to their capability to capture long-term dependencies. However, prior work has been confined to modeling temporal dependencies at either a fixed scale or multiple scales that exponentially increase (most with base 2). This limitation hinders their effectiveness in capturing diverse seasonalities, such as hourly and daily patterns. In this paper, we introduce a dimension invariant embedding technique that captures short-term temporal dependencies and projects MTS data into a higher-dimensional space, while preserving the dimensions of time steps and variables in MTS data. Furthermore, we present a novel Multi-scale Transformer Pyramid Network (MTPNet), specifically designed to effectively capture temporal dependencies at multiple unconstrained scales. The predictions are inferred from multi-scale latent representations obtained from transformers at various scales. Extensive experiments on nine benchmark datasets demonstrate that the proposed MTPNet outperforms recent state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2308.11946

Code (1)

GRYGY1215/MTPNet 공식 구현 pytorch

Tasks

Multivariate Time Series ForecastingTime SeriesTime Series Forecasting

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
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…
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
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…

Similar Papers 제목 키워드 기반

PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting

2024-08-20 · Yongbo Yu, Weizhong Yu, Feiping Nie, Xuelong Li

The self-attention mechanism in Transformer architecture, invariant to sequence order, necessitates positional embeddings to encode temporal order in time series prediction. We argue that this reliance on positional embe…

Multivariate Time Series ForecastingTemporal SequencesTime SeriesTime Series Forecasting+1

DPANet: Dual Pyramid Attention Network for Multivariate Time Series Forecasting

2025-09-18 · Qianyang Li, Xingjun Zhang, Shaoxun Wang, Jia Wei arxiv

Long-term time series forecasting (LTSF) is hampered by the challenge of modeling complex dependencies that span multiple temporal scales and frequency resolutions. Existing methods, including Transformer and MLP-based m…

Multivariate Time Series ForecastingRepresentation Learning

Deep Learning for Multi-Scale Changepoint Detection in Multivariate Time Series

2019-05-16 · Zahra Ebrahimzadeh, Min Zheng, Selcuk Karakas, Samantha Kleinberg

Many real-world time series, such as in health, have changepoints where the system's structure or parameters change. Since changepoints can indicate critical events such as onset of illness, it is highly important to det…

Time SeriesTime Series Analysis

PyramidStyler: Transformer-Based Neural Style Transfer with Pyramidal Positional Encoding and Reinforcement Learning

2025-10-02 · Raahul Krishna Durairaju, K. Saruladha arxiv

Neural Style Transfer (NST) has evolved from Gatys et al.'s (2015) CNN-based algorithm, enabling AI-driven artistic image synthesis. However, existing CNN and transformer-based models struggle to scale efficiently to com…

Reinforcement LearningStyle Transfer

Multi-direction and Multi-scale Pyramid in Transformer for Video-based Pedestrian Retrieval

2022-02-12 · Xianghao Zang, Ge Li, Wei Gao

In video surveillance, pedestrian retrieval (also called person re-identification) is a critical task. This task aims to retrieve the pedestrian of interest from non-overlapping cameras. Recently, transformer-based model…

Person Re-IdentificationRetrieval