Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting

Oreshkin, Boris N.; Carpov, Dmitri; Chapados, Nicolas; Bengio, Yoshua

doi:10.1609/aaai.v35i10.17115

Cited by 88 publications

(126 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The suggested nonlinear method in this study is a novel algorithm based on a deep neural network structure. Oreshkin et al (2019) developed the neural basis expansion analysis for interpretable time series forecasting (N-BEATS). That is, a deep learning method explicitly developed to produce univariate time series point forecasting.…”

Section: Methodsmentioning

confidence: 99%

“…That is, in forecasting competitions tree methods (gradient and eXtreme gradient tree boosting) or more modern deep learning methods such as modified artificial or recurrent neural networks showed superior forecasting performance and dominated the field. Oreshkin et al (2019) present a deep neural network architecture (neural basis expansion analysis for interpretable time series forecasting -N-BEATS) that demonstrates state-of-the-art performance on statistical benchmarks. In a practical application, Oreshkin et al (2020) employ the developed N-BEATS to 35 electricity demand time series for European markets and find that the neural network outperforms all competitors (classical statistical methods, machine learning, hybrid approaches) regarding the forecast accuracy and bias.…”

Section: Univariate Time Series Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Forecasting office rents with ensemble models – the case for European real estate markets

Ahlefeldt-Dehn

Cajias²,

Schäfers³

2022

JPIF

View full text Add to dashboard Cite

PurposeCommercial real estate and office rental values, in particular, have long been the focus of research. Several forecasting frameworks for office rental values in multivariate and univariate fashions have been proposed. Recent developments in time series forecasting using machine learning and deep learning methods offer an opportunity to update traditional univariate forecasting frameworks.Design/methodology/approachWith the aim to extend research on univariate rent forecasting a hybrid methodology combining both ARIMA and a neural network model is proposed to exploit the unique strengths of both methods in linear and nonlinear modelling. N-BEATS, a deep learning algorithm that has demonstrated state-of-the-art forecasting performance in major forecasting competitions, are explained. With the ARIMA model, it is jointly applied to the office rental dataset to produce forecasts for four-quarters ahead.FindingsWhen the approach is applied to a dataset of 21 major European office cities, the results show that the ensemble model can be an effective approach to improve the prediction accuracy achieved by each of the models used separately.Practical implicationsReal estate forecasting is essential for assessing the value of managing portfolios and for evaluating investment strategies. The approach applied in this paper confirms the heterogeneity of real estate markets. The application of mixed modelling via linear and nonlinear methods decreases the uncertainty of abrupt changes in rents.Originality/valueTo the best of the authors' knowledge, no such application of a hybrid model updating classical statistical forecasting with a deep learning neural network approach in the field of commercial real estate rent forecasting has been undertaken.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Univariate Time Series Modelsmentioning

confidence: 99%

Forecasting office rents with ensemble models – the case for European real estate markets

Ahlefeldt-Dehn

Cajias²,

Schäfers³

2022

JPIF

View full text Add to dashboard Cite

show abstract

“…The gated recurrent unit network (GRU) [19] which is another variation of RNN. The neural basis analysis for time-series model (N-BEATS) [18]. The Transformer [22] which uses attention.…”

Section: 𝑡 𝑘 𝑡 𝑡mentioning

confidence: 99%

A benchmark of individual auto-regressive models in a massive fMRI dataset

Paugam¹,

Pinsard²,

Lajoie³

et al. 2023

Preprint

View full text Add to dashboard Cite

Dense functional magnetic resonance imaging datasets open new avenues to create auto-regressive models of brain activity. Individual idiosyncrasies are obscured by group models, but can be captured by purely individual models given sufficient amounts of training data. In this study, we compared several deep and shallow individual models on the auto-regression of BOLD time series recorded during a natural video watching task. The best performing models were then analyzed in terms of their data requirements and scaling, subject specificity and the space-time structure of their predicted dynamics.We found the Chebnets, a type of graph convolutional neural network, to be best suited for BOLD auto-regression, closely followed by linear models. Chebnets demonstrated an increase in performance with increasing amounts of data, with no complete saturation at 9 h of training data. Significant subject specificity was found at short prediction time lags. The Chebnets were found to capture lower frequencies at longer prediction time lags, and the spatial correlations in predicted dynamics were found to match traditional functional connectivity networks.Overall, these results demonstrate that large individual fMRI datasets can be used to efficiently train purely individual auto-regressive models of brain activity, and that massive amounts of individual data are required to do so. The excellent performance of the Chebnets likely reflects their ability to combine spatial and temporal interactions on large time scales at a low complexity cost. Individual auto-regressive models have the potential to improve our understanding of the functional interactions in the human brain. This study is based on a massive, publicly-available dataset, which can serve for future benchmarks of individual auto-regressive modeling.

show abstract

“…Time series forecasting approaches are therefore used. In this context, Oreshkin et al [65] proposed a metalearning framework for univariate time series forecasting when no target data are available. In our work, energy consumption data are multivariate due to the numerous involved factors.…”

Section: Related Workmentioning

confidence: 99%

Query-adaptive training data recommendation for cross-building predictive modeling

et al. 2022

View full text Add to dashboard Cite

Predictive modeling in buildings is a key task for the optimal management of building energy. Relevant building operational data are a prerequisite for such task, notably when deep learning is used. However, building operational data are not always available, such is the case in newly built, newly renovated, or even not yet built buildings. To address this problem, we propose a deep similarity learning approach to recommend relevant training data to a target building solely by using a minimal contextual description on it. Contextual descriptions are modeled as user queries. We further propose to ensemble most used machine learning algorithms in the context of predictive modeling. This contributes to the genericity of the proposed methodology. Experimental evaluations show that our methodology offers a generic methodology for cross-building predictive modeling and achieves good generalization performance.Keywords Training data recommendation • similarity learning • domain generalization • knowledge transfer • data-driven modeling • building energy.

show abstract

Meta-Learning Framework with Applications to Zero-Shot Time-Series Forecasting

Cited by 88 publications

References 27 publications

Forecasting office rents with ensemble models – the case for European real estate markets

Forecasting office rents with ensemble models – the case for European real estate markets

A benchmark of individual auto-regressive models in a massive fMRI dataset

Query-adaptive training data recommendation for cross-building predictive modeling

Contact Info

Product

Resources

About