Curricular and Cyclical Loss for Time Series Learning Strategy

• URL: http://arxiv.org/abs/2312.15853v1
• Date: Tue, 26 Dec 2023 02:40:05 GMT
• Title: Curricular and Cyclical Loss for Time Series Learning Strategy
• Authors: Chenxi Sun, Hongyan Li, Moxian Song, Derun Cai, Shenda Hong
• Abstract summary: We propose a novel Curricular and CyclicaL loss (CRUCIAL) to learn time series for the first time. CRUCIAL has two characteristics: It can arrange an easy-to-hard learning order and achieve an adaptive cycle. We prove that compared with monotonous size, cyclical size can reduce expected error.
• Score: 17.725840333187577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series widely exists in real-world applications and many deep learning models have performed well on it. Current research has shown the importance of learning strategy for models, suggesting that the benefit is the order and size of learning samples. However, no effective strategy has been proposed for time series due to its abstract and dynamic construction. Meanwhile, the existing one-shot tasks and continuous tasks for time series necessitate distinct learning processes and mechanisms. No all-purpose approach has been suggested. In this work, we propose a novel Curricular and CyclicaL loss (CRUCIAL) to learn time series for the first time. It is model- and task-agnostic and can be plugged on top of the original loss with no extra procedure. CRUCIAL has two characteristics: It can arrange an easy-to-hard learning order by dynamically determining the sample contribution and modulating the loss amplitude; It can manage a cyclically changed dataset and achieve an adaptive cycle by correlating the loss distribution and the selection probability. We prove that compared with monotonous size, cyclical size can reduce expected error. Experiments on 3 kinds of tasks and 5 real-world datasets show the benefits of CRUCIAL for most deep learning models when learning time series.

Related papers

• Adaptive Rentention & Correction for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task. We name our approach Adaptive Retention & Correction (ARC) ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• Distillation Enhanced Time Series Forecasting Network with Momentum Contrastive Learning [7.4106801792345705]
  We propose DE-TSMCL, an innovative distillation enhanced framework for long sequence time series forecasting. Specifically, we design a learnable data augmentation mechanism which adaptively learns whether to mask a timestamp. Then, we propose a contrastive learning task with momentum update to explore inter-sample and intra-temporal correlations of time series. By developing model loss from multiple tasks, we can learn effective representations for downstream forecasting task.
  arXiv  Detail & Related papers  (2024-01-31T12:52:10Z)
• Learning the Dynamics of Sparsely Observed Interacting Systems [0.6021787236982659]
  We address the problem of learning the dynamics of an unknown non-parametric system linking a target and a feature time series. By leveraging the rich theory of signatures, we are able to cast this non-linear problem as a high-dimensional linear regression.
  arXiv  Detail & Related papers  (2023-01-27T10:48:28Z)
• NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research [96.53307645791179]
  We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
  arXiv  Detail & Related papers  (2022-11-15T18:57:46Z)
• Learning Mixtures of Linear Dynamical Systems [94.49754087817931]
  We develop a two-stage meta-algorithm to efficiently recover each ground-truth LDS model up to error $tildeO(sqrtd/T)$. We validate our theoretical studies with numerical experiments, confirming the efficacy of the proposed algorithm.
  arXiv  Detail & Related papers  (2022-01-26T22:26:01Z)
• An Empirical Investigation of the Role of Pre-training in Lifelong Learning [21.995593026269578]
  We show that generic pre-training implicitly alleviates the effects of catastrophic forgetting when learning multiple tasks sequentially. We study this phenomenon by analyzing the loss landscape, finding that pre-trained weights appear to ease forgetting by leading to wider minima.
  arXiv  Detail & Related papers  (2021-12-16T19:00:55Z)
• Multimodal Meta-Learning for Time Series Regression [3.135152720206844]
  We will explore the idea of using meta-learning for quickly adapting model parameters to new short-history time series. We show empirically that our proposed meta-learning method learns TSR with few data fast and outperforms the baselines in 9 of 12 experiments.
  arXiv  Detail & Related papers  (2021-08-05T20:50:18Z)
• 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)
• Learning summary features of time series for likelihood free inference [93.08098361687722]
  We present a data-driven strategy for automatically learning summary features from time series data. Our results indicate that learning summary features from data can compete and even outperform LFI methods based on hand-crafted values.
  arXiv  Detail & Related papers  (2020-12-04T19:21:37Z)
• Meta Cyclical Annealing Schedule: A Simple Approach to Avoiding Meta-Amortization Error [50.83356836818667]
  We develop a novel meta-regularization objective using it cyclical annealing schedule and it maximum mean discrepancy (MMD) criterion. The experimental results show that our approach substantially outperforms standard meta-learning algorithms.
  arXiv  Detail & Related papers  (2020-03-04T04:43:16Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

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.