Related papers: ReFine: Boosting Time Series Prediction of Extreme Events by Reweighting and Fine-tuning

ReFine: Boosting Time Series Prediction of Extreme Events by Reweighting and Fine-tuning

URL: http://arxiv.org/abs/2409.14232v1
Date: Sat, 21 Sep 2024 19:29:29 GMT
Title: ReFine: Boosting Time Series Prediction of Extreme Events by Reweighting and Fine-tuning
Authors: Jimeng Shi, Azam Shirali, Giri Narasimhan,
Abstract summary: Extreme events are of great importance since they represent impactive occurrences. accurately predicting these extreme events is challenging due to their rarity and irregularity. We propose two strategies, reweighting and fine-tuning, to tackle the challenge.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Extreme events are of great importance since they often represent impactive occurrences. For instance, in terms of climate and weather, extreme events might be major storms, floods, extreme heat or cold waves, and more. However, they are often located at the tail of the data distribution. Consequently, accurately predicting these extreme events is challenging due to their rarity and irregularity. Prior studies have also referred to this as the out-of-distribution (OOD) problem, which occurs when the distribution of the test data is substantially different from that used for training. In this work, we propose two strategies, reweighting and fine-tuning, to tackle the challenge. Reweighting is a strategy used to force machine learning models to focus on extreme events, which is achieved by a weighted loss function that assigns greater penalties to the prediction errors for the extreme samples relative to those on the remainder of the data. Unlike previous intuitive reweighting methods based on simple heuristics of data distribution, we employ meta-learning to dynamically optimize these penalty weights. To further boost the performance on extreme samples, we start from the reweighted models and fine-tune them using only rare extreme samples. Through extensive experiments on multiple data sets, we empirically validate that our meta-learning-based reweighting outperforms existing heuristic ones, and the fine-tuning strategy can further increase the model performance. More importantly, these two strategies are model-agnostic, which can be implemented on any type of neural network for time series forecasting. The open-sourced code is available at \url{https://github.com/JimengShi/ReFine}.

Related papers

Evaluating the Role of Data Enrichment Approaches Towards Rare Event Analysis in Manufacturing [1.3980986259786223]
Rare events are occurrences that take place with a significantly lower frequency than more common regular events. In manufacturing, predicting such events is particularly important, as they lead to unplanned downtime, shortening equipment lifespan, and high energy consumption. This paper evaluates the role of data enrichment techniques combined with supervised machine-learning techniques for rare event detection and prediction.
arXiv Detail & Related papers (2024-07-01T00:05:56Z)
Reducing Bias in Pre-trained Models by Tuning while Penalizing Change [8.862970622361747]
Deep models trained on large amounts of data often incorporate implicit biases present during training time. New data is often expensive and hard to come by in areas such as autonomous driving or medical decision-making. We present a method based on change penalization that takes a pre-trained model and adapts the weights to mitigate a previously detected bias.
arXiv Detail & Related papers (2024-04-18T16:12:38Z)
Ask Your Distribution Shift if Pre-Training is Right for You [74.18516460467019]
In practice, fine-tuning a pre-trained model improves robustness significantly in some cases but not at all in others. We focus on two possible failure modes of models under distribution shift: poor extrapolation and biases in the training data. Our study suggests that, as a rule of thumb, pre-training can help mitigate poor extrapolation but not dataset biases.
arXiv Detail & Related papers (2024-02-29T23:46:28Z)
A non-intrusive machine learning framework for debiasing long-time coarse resolution climate simulations and quantifying rare events statistics [0.0]
coarse models suffer from inherent bias due to the ignored "sub-grid" scales. We propose a framework to non-intrusively debias coarse-resolution climate predictions using neural-network (NN) correction operators.
arXiv Detail & Related papers (2024-02-28T17:06:19Z)
ExtremeCast: Boosting Extreme Value Prediction for Global Weather Forecast [57.6987191099507]
We introduce Exloss, a novel loss function that performs asymmetric optimization and highlights extreme values to obtain accurate extreme weather forecast. We also introduce ExBooster, which captures the uncertainty in prediction outcomes by employing multiple random samples. Our solution can achieve state-of-the-art performance in extreme weather prediction, while maintaining the overall forecast accuracy comparable to the top medium-range forecast models.
arXiv Detail & Related papers (2024-02-02T10:34:13Z)
An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks [6.5700527395783315]
We propose a novel probability-enhanced neural network model, called NEC+, which concurrently learns extreme and normal prediction functions. We evaluate the proposed model on the difficult 3-day ahead hourly water level prediction task applied to 9 reservoirs in California.
arXiv Detail & Related papers (2022-11-29T03:01:59Z)
Output-weighted and relative entropy loss functions for deep learning precursors of extreme events [0.0]
We propose a novel loss function, the adjusted output weighted loss, and extend the applicability of relative entropy based loss functions to systems with low dimensional output. The proposed functions are tested using several cases of dynamical systems exhibiting extreme events and shown to significantly improve accuracy in predictions of extreme events.
arXiv Detail & Related papers (2021-12-01T21:05:54Z)
Improved Fine-tuning by Leveraging Pre-training Data: Theory and Practice [52.11183787786718]
Fine-tuning a pre-trained model on the target data is widely used in many deep learning applications. Recent studies have empirically shown that training from scratch has the final performance that is no worse than this pre-training strategy. We propose a novel selection strategy to select a subset from pre-training data to help improve the generalization on the target task.
arXiv Detail & Related papers (2021-11-24T06:18:32Z)
Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift [81.74795324629712]
We call prediction-time batch normalization, which significantly improves model accuracy and calibration under covariate shift. We show that prediction-time batch normalization provides complementary benefits to existing state-of-the-art approaches for improving robustness. The method has mixed results when used alongside pre-training, and does not seem to perform as well under more natural types of dataset shift.
arXiv Detail & Related papers (2020-06-19T05:08:43Z)
Learning a Unified Sample Weighting Network for Object Detection [113.98404690619982]
Region sampling or weighting is significantly important to the success of modern region-based object detectors. We argue that sample weighting should be data-dependent and task-dependent. We propose a unified sample weighting network to predict a sample's task weights.
arXiv Detail & Related papers (2020-06-11T16:19:16Z)
Ambiguity in Sequential Data: Predicting Uncertain Futures with Recurrent Models [110.82452096672182]
We propose an extension of the Multiple Hypothesis Prediction (MHP) model to handle ambiguous predictions with sequential data. We also introduce a novel metric for ambiguous problems, which is better suited to account for uncertainties.
arXiv Detail & Related papers (2020-03-10T09:15:42Z)

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