On the Regularization of Learnable Embeddings for Time Series Forecasting

• URL: http://arxiv.org/abs/2410.14630v2
• Date: Thu, 13 Feb 2025 10:43:50 GMT
• Title: On the Regularization of Learnable Embeddings for Time Series Forecasting
• 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 attempting to prevent the co-adaptation of local and global parameters by means of embeddings perturbation are particularly effective in this context.
• Score: 18.069747511100132
• License:
• Abstract: In forecasting 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 attempting to prevent the co-adaptation of local and global parameters by means of embeddings perturbation are particularly effective in this context. In this regard, we include in the comparison several perturbation-based regularization methods, going as far as periodically 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

• Towards Generalisable Time Series Understanding Across Domains [10.350643783811174]
  We introduce a novel pre-training paradigm specifically designed to handle time series heterogeneity. We propose a tokeniser with learnable domain signatures, a dual masking strategy, and a normalised cross-correlation loss. Our code and pre-trained weights are available at https://www.oetu.com/oetu/otis.
  arXiv  Detail & Related papers  (2024-10-09T17:09:30Z)
• 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)
• Robust Detection of Lead-Lag Relationships in Lagged Multi-Factor Models [61.10851158749843]
  Key insights can be obtained by discovering lead-lag relationships inherent in the data. We develop a clustering-driven methodology for robust detection of lead-lag relationships in lagged multi-factor models.
  arXiv  Detail & Related papers  (2023-05-11T10:30:35Z)
• 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)
• Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding [8.45908939323268]
  We propose a self-supervised framework for learning generalizable representations for non-stationary time series. Our motivation stems from the medical field, where the ability to model the dynamic nature of time series data is especially valuable.
  arXiv  Detail & Related papers  (2021-06-01T19:53:24Z)

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.