On the Regularization of Learnable Embeddings for Time Series Processing

• URL: http://arxiv.org/abs/2410.14630v1
• Date: Fri, 18 Oct 2024 17:30:20 GMT
• Title: On the Regularization of Learnable Embeddings for Time Series Processing
• Authors: Luca Butera, Giovanni De Felice, Andrea Cini, Cesare Alippi,
• Abstract summary: We investigate methods to regularize the learning of local learnable embeddings for time series processing. We show that methods preventing the co-adaptation of local and global parameters are particularly effective in this context.
• Score: 18.069747511100132
• License:
• Abstract: In processing multiple time series, accounting for the individual features of each sequence can be challenging. To address this, modern deep learning methods for time series analysis combine a shared (global) model with local layers, specific to each time series, often implemented as learnable embeddings. Ideally, these local embeddings should encode meaningful representations of the unique dynamics of each sequence. However, when these are learned end-to-end as parameters of a forecasting model, they may end up acting as mere sequence identifiers. Shared processing blocks may then become reliant on such identifiers, limiting their transferability to new contexts. In this paper, we address this issue by investigating methods to regularize the learning of local learnable embeddings for time series processing. Specifically, we perform the first extensive empirical study on the subject and show how such regularizations consistently improve performance in widely adopted architectures. Furthermore, we show that methods preventing the co-adaptation of local and global parameters are particularly effective in this context. This hypothesis is validated by comparing several methods preventing the downstream models from relying on sequence identifiers, going as far as completely resetting the embeddings during training. The obtained results provide an important contribution to understanding the interplay between learnable local parameters and shared processing layers: a key challenge in modern time series processing models and a step toward developing effective foundation models for time series.

Related papers

• UniCL: A Universal Contrastive Learning Framework for Large Time Series Models [18.005358506435847]
  Time-series analysis plays a pivotal role across a range of critical applications, from finance to healthcare. Traditional supervised learning methods first annotate extensive labels for time-series data in each task. This paper introduces UniCL, a universal and scalable contrastive learning framework designed for pretraining time-series foundation models.
  arXiv  Detail & Related papers  (2024-05-17T07:47:11Z)
• Advancing Time Series Classification with Multimodal Language Modeling [6.624754582682479]
  We propose InstructTime, a novel attempt to reshape time series classification as a learning-to-generate paradigm. The core idea is to formulate the classification of time series as a multimodal understanding task, in which both task-specific instructions and raw time series are treated as multimodal inputs. Extensive experiments are conducted over benchmark datasets, whose results uncover the superior performance of InstructTime.
  arXiv  Detail & Related papers  (2024-03-19T02:32:24Z)
• TimeSiam: A Pre-Training Framework for Siamese Time-Series Modeling [67.02157180089573]
  Time series pre-training has recently garnered wide attention for its potential to reduce labeling expenses and benefit various downstream tasks. This paper proposes TimeSiam as a simple but effective self-supervised pre-training framework for Time series based on Siamese networks.
  arXiv  Detail & Related papers  (2024-02-04T13:10:51Z)
• Real-World Compositional Generalization with Disentangled Sequence-to-Sequence Learning [81.24269148865555]
  A recently proposed Disentangled sequence-to-sequence model (Dangle) shows promising generalization capability. We introduce two key modifications to this model which encourage more disentangled representations and improve its compute and memory efficiency. Specifically, instead of adaptively re-encoding source keys and values at each time step, we disentangle their representations and only re-encode keys periodically.
  arXiv  Detail & Related papers  (2022-12-12T15:40:30Z)
• Learning Sequence Representations by Non-local Recurrent Neural Memory [61.65105481899744]
  We propose a Non-local Recurrent Neural Memory (NRNM) for supervised sequence representation learning. Our model is able to capture long-range dependencies and latent high-level features can be distilled by our model. Our model compares favorably against other state-of-the-art methods specifically designed for each of these sequence applications.
  arXiv  Detail & Related papers  (2022-07-20T07:26:15Z)
• Cluster-and-Conquer: A Framework For Time-Series Forecasting [94.63501563413725]
  We propose a three-stage framework for forecasting high-dimensional time-series data. Our framework is highly general, allowing for any time-series forecasting and clustering method to be used in each step. When instantiated with simple linear autoregressive models, we are able to achieve state-of-the-art results on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T20:41:19Z)
• Novel Features for Time Series Analysis: A Complex Networks Approach [62.997667081978825]
  Time series data are ubiquitous in several domains as climate, economics and health care. Recent conceptual approach relies on time series mapping to complex networks. Network analysis can be used to characterize different types of time series.
  arXiv  Detail & Related papers  (2021-10-11T13:46:28Z)
• Time Series Analysis via Network Science: Concepts and Algorithms [62.997667081978825]
  This review provides a comprehensive overview of existing mapping methods for transforming time series into networks. We describe the main conceptual approaches, provide authoritative references and give insight into their advantages and limitations in a unified notation and language. Although still very recent, this research area has much potential and with this survey we intend to pave the way for future research on the topic.
  arXiv  Detail & Related papers  (2021-10-11T13:33:18Z)
• Multi-Time Attention Networks for Irregularly Sampled Time Series [18.224344440110862]
  Irregular sampling occurs in many time series modeling applications. We propose a new deep learning framework for this setting that we call Multi-Time Attention Networks. Our results show that our approach performs as well or better than a range of baseline and recently proposed models.
  arXiv  Detail & Related papers  (2021-01-25T18:57:42Z)
• Multi-Faceted Representation Learning with Hybrid Architecture for Time Series Classification [16.64345034889185]
  We propose a hybrid neural architecture, called Self-Attentive Recurrent Convolutional Networks (SARCoN) SARCoN is the synthesis of long short-term memory networks with self-attentive mechanisms and Fully Convolutional Networks. Our work provides a novel angle that deepens the understanding of time series classification, qualifying our proposed model as an ideal choice for real-world applications.
  arXiv  Detail & Related papers  (2020-12-21T16:42:07Z)
• Interpretable Time Series Classification using Linear Models and Multi-resolution Multi-domain Symbolic Representations [6.6147550436077776]
  We propose new time series classification algorithms to address gaps in current approaches. Our approach is based on symbolic representations of time series, efficient sequence mining algorithms and linear classification models. Our models are as accurate as deep learning models but are more efficient regarding running time and memory, can work with variable-length time series and can be interpreted by highlighting the discriminative symbolic features on the original time series.
  arXiv  Detail & Related papers  (2020-05-31T15:32:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.