paper-with-me

Papers

Latent Processes Identification From Multi-View Time Series

2023-05-14 · Zenan Huang, Haobo Wang, Junbo Zhao, Nenggan Zheng

Understanding the dynamics of time series data typically requires identifying the unique latent factors for data generation, \textit{a.k.a.}, latent processes identification. Driven by the independent assumption, existing works have made great progress in handling single-view data. However, it is a non-trivial problem that extends them to multi-view time series data because of two main challenges: (i) the complex data structure, such as temporal dependency, can result in violation of the independent assumption; (ii) the factors from different views are generally overlapped and are hard to be aggregated to a complete set. In this work, we propose a novel framework MuLTI that employs the contrastive learning technique to invert the data generative process for enhanced identifiability. Additionally, MuLTI integrates a permutation mechanism that merges corresponding overlapped variables by the establishment of an optimal transport formula. Extensive experimental results on synthetic and real-world datasets demonstrate the superiority of our method in recovering identifiable latent variables on multi-view time series.

📄 PDF Abstract BibTeX arXiv:2305.08164

Code (1)

lccurious/MuLTI 공식 구현 pytorch

Tasks

Contrastive LearningTime Series

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

Learning Nonparametric Volterra Kernels with Gaussian Processes

2021-06-10 · NeurIPS 2021 12 · Magnus Ross, Michael T. Smith, Mauricio A. Álvarez

This paper introduces a method for the nonparametric Bayesian learning of nonlinear operators, through the use of the Volterra series with kernels represented using Gaussian processes (GPs), which we term the nonparametr…

Gaussian ProcessesNumerical IntegrationregressionVariational Inference

Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism

2025-05-12 · Ruichu Cai, Kaitao Zheng, Junxian Huang, Zijian Li 외

Time series imputation is one of the most challenge problems and has broad applications in various fields like health care and the Internet of Things. Existing methods mainly aim to model the temporally latent dependenci…

ImputationTime SeriesVariational Inference

Runner re-identification from single-view running video in the open-world setting

2023-10-18 · Tomohiro Suzuki, Kazushi Tsutsui, Kazuya Takeda, Keisuke Fujii

In many sports, player re-identification is crucial for automatic video processing and analysis. However, most of the current studies on player re-identification in multi- or single-view sports videos focus on re-identif…

Recurrent Neural Processes

2019-06-13 · Timon Willi, Jonathan Masci, Jürgen Schmidhuber, Christian Osendorfer

We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Given time series observed on fast real-wor…

Gaussian ProcessesState Space ModelsTime SeriesTime Series Analysis

On the Identification of Temporally Causal Representation with Instantaneous Dependence

2024-05-24 · Zijian Li, Yifan Shen, Kaitao Zheng, Ruichu Cai 외

Temporally causal representation learning aims to identify the latent causal process from time series observations, but most methods require the assumption that the latent causal processes do not have instantaneous relat…

Motion ForecastingRepresentation LearningTime SeriesVariational Inference