Boosted Embeddings for Time Series Forecasting

  title={Boosted Embeddings for Time Series Forecasting},
  author={Sankeerth Rao Karingula and Nandini Ramanan and Rasool Tahsambi and Mehrnaz Amjadi and Deokwoo Jung and Ricky Si and Charanraj Thimmisetty and Claudionor Nunes Coelho},
  booktitle={International Conference on Machine Learning, Optimization, and Data Science},
Time series forecasting is a fundamental task emerging from diverse data-driven applications. Many advanced autoregressive methods such as ARIMA[8] were used to develop forecasting models. Recently, deep learning based methods such as DeepAr[16], NeuralProphet[1], Seq2Seq [30] have been explored for time series forecasting problem. In this paper, we propose a novel time series forecast model, DeepGB. We formulate and implement a variant of Gradient boosting [18] wherein the weak learners are… 

Time Series Anomaly Detection with label-free Model Selection

LaF-AD is proposed, a novel anomaly detection algorithm with labelfree model selection for unlabeled times-series data that performs a fully unsupervised ensemble learning across a large number of candidate parametric models and develops a model variance metric that quantifies the sensitivity of anomaly probability with a bootstrapping method.

A Differentiable Neural-Network Force Field for Ionic Liquids

The possibility of training on small data sets allows for an ensemble-learning approach to the detection of extrapolation, and it is found that a separate treatment of long-range interactions is not required to achieve a high-quality representation of the potential energy surface of these dense ionic systems.

Time-Series Forecasting With Shape Attention*

The experimental results conducted on two datasets show that the performance of SADC model outperforms the state-of-the-art models on time series forecasting.

Unsupervised Anomaly Detection for Auditing Data and Impact of Categorical Encodings

This paper introduces the Vehicle Claims dataset, consisting of fraudulent insurance claims for automotive repairs, and compares competitive learning, reconstruction-error, density estimation and contrastive learning approaches for Label, One Hot, GEL encoding and embedding layer to handle categorical values.

Real-time Drift Detection on Time-series Data

This work proposes an approach called Unsupervised Temporal Drift Detector or UTDD to flexibly account for seasonal variation, efficiently detect temporal concept drift in time series data in the absence of ground truth, and subsequently adapt the authors' ML models to concept drift for better generalization.



Time-series forecasting with deep learning: a survey

This article surveys common encoder and decoder designs used in both one-step-ahead and multi-horizon time-series forecasting—describing how temporal information is incorporated into predictions by each model.

Probabilistic Forecasting with Temporal Convolutional Neural Network

AR-Net: A simple Auto-Regressive Neural Network for time-series

A new framework for time-series modeling that combines the best of traditional statistical models and neural networks is presented, and it is shown that AR-Net is as interpretable as Classic-AR but also scales to long-range dependencies.

Recurrent Neural Networks for Time Series Forecasting: Current Status and Future Directions

Time Series Forecasting Using LSTM Networks: A Symbolic Approach

It is shown that the symbolic representation can help to alleviate some of the aforementioned problems and, in addition, might allow for faster training without sacrificing the forecast performance.

Boosted Convolutional Neural Networks

This work proposes a novel algorithm to incorporate boosting weights into the deep learning architecture based on least squares objective function and shows that it is possible to use networks of different structures within the proposed boosting framework and BoostCNN is able to select the best network structure in each iteration.

COVID-19 Future Forecasting Using Supervised Machine Learning Models

The results prove that the ES performs best among all the used models followed by LR and LASSO which performs well in forecasting the new confirmed cases, death rate as well as recovery rate, while SVM performs poorly in all the prediction scenarios given the available dataset.

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.

node2vec: Scalable Feature Learning for Networks

In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.