MLAT improves kNN performance in time series by learning metrics that align and capture temporal dependencies.
problem Improving kNN performance in time series by learning metrics that effectively handle variations and temporal dependencies.
method MLAT uses a sliding window to augment time series data and applies time-invariant metric learning to derive the most appropriate distance measure.
result MLAT outperforms other existing algorithms in various real-world data sets.
This work benchmarks counterfactual methods in time series classification.
problem Lack of benchmarking studies for counterfactual methods in time series classification.
method Redesign metrics for sparsity, plausibility, and consistency; systematically benchmark 6 CF methods on 30 datasets.
result Performance of CF methods varies across metrics and models.
Study evaluates local explanation methods for time series forecasting.
problem Lack of local interpretability methods for multivariate time series forecasting.
method Proposed two novel evaluation metrics: Area Over the Perturbation Curve for Regression and Ablation Percentage Threshold.
result Comprehensive comparison of local explanation models on two datasets.
timeXplain bridges AI and time series, making predictions understandable.
problem Making time series classifier predictions interpretable.
method Developed a framework that combines time series data with model-agnostic explainers.
result timeXplain improves the interpretability of time series classifiers.
New method learns routines from inertial data without privacy concerns.
problem Recognizing human activities with limited sets of specific activities.
method Metric learning problem defined for time series, SS2S architecture.
result Clustering recovers daily routines from learned distance.
New time series generation models improve accuracy and correlation identification.
problem Generating accurate and correlated time series from limited data.
method Conditional Euler Generator (CEGEN) using Euler discretization of SDEs and Wasserstein metrics.
result CEGEN outperforms state-of-the-art models on various metrics and real-world datasets.
A new robust time series distance metric for k-NN classification.
problem Robustness against arbitrary data contamination in time series classification.
method Proposes a novel distance metric with worst-case O(nlogn) complexity. result Demonstrates competitive classification accuracy in k-NN time series classification.
Study geodesic properties of time series data using Wasserstein metric.
problem Modeling nonlinear time series with transport-based metrics.
method Generalized Wasserstein metric and signed cumulative distribution transforms.
result Geodesic properties provide added interpretability and robustness in time series classifiers.
Study reveals class-dependent effects in perturbation-based feature attribution metrics for time series classification.
problem Varying effectiveness of perturbation-based metrics across different classes in time series models.
method Systematic empirical analysis across multiple datasets, model architectures, and perturbation strategies.
result Perturbation-based metrics show varying effectiveness across classes, with some metrics performing better for certain classes.
This paper reviews causal inference methods for time series data.
problem Estimating treatment effects and identifying causal relations from time series data.
method Comprehensive review of approaches for treatment effect estimation and causal discovery.
result Provides a list of evaluation metrics and datasets for time series causal inference.
MegazordNet combines stats and ML for better financial time series forecasting.
problem Forecasting financial time series is challenging due to its chaotic nature.
method MegazordNet integrates statistical features with a deep learning model.
result MegazordNet outperforms single statistical and machine learning methods in S&P 500 stock price prediction.
Paper establishes a comprehensive benchmark for ECG time-series analysis.
problem Incomplete understanding of ECG signal properties and limitations in evaluation metrics.
method Categorization of downstream applications, identification of limitations, introduction of a novel metric, benchmarking of time-series models.
result Validation of the effectiveness of the proposed metric and model architecture.
An image-driven approach for time series forecasting.
problem Time-series forecasting as a computer vision task.
method Capture input data as an image and train a model to produce the subsequent image.
result Our method outperforms various baselines, including ARIMA, using image-based evaluation metrics.
New method uses nested optimal transport for financial time series evaluation.
problem Lack of consensus metric for evaluating generative models in finance.
method Nested optimal transport distance for time-causal tasks, with a parallelizable algorithm.
result Substantial speedups and robustness to financial tasks.
A new metric measures time series divergence efficiently.
problem Quantifying subtle differences in time series data.
method Sequence Likelihood (SL) divergence, a generalized KL divergence for time series.
result Efficient estimators of SL divergence from finite sample paths.
Proposes GDTW for aligning time series on different, incomparable spaces.
problem Dynamic time warping requires comparable spaces, but time series can live on different, incomparable spaces.
method Gromov dynamic time warping (GDTW) considers intra-relational geometry to avoid comparability requirements.
result Demonstrates effectiveness of GDTW in aligning, combining, and comparing time series on incomparable spaces.
Paper introduces metrics to evaluate missing data imputation without ground truth.
problem Handling missing data in time series without ground truth.
method Introduces Wasserstein distance (WD) and Jensen-Shannon divergence (JSD) as metrics to evaluate imputation quality.
result WD and JSD are effective metrics for assessing missing data imputation quality.
This paper evaluates anomaly detection methods for multivariate time series data.
problem Lack of systematic comparison of anomaly detection methods on multivariate time series data.
method Comprehensive evaluation of 10 models and 4 scoring functions on 10 datasets.
result Dynamic scoring functions outperform static ones, and the choice of scoring functions matters more than the model choice.
Benchmark study evaluates 8 clustering methods on 99 UCR time series datasets.
problem Assessing the performance of clustering methods on time series data.
method Examines 8 clustering methods across 3 categories and 3 distance measures on 99 UCR datasets.
result Provides a comprehensive dataset-level assessment of clustering methods.
Paper introduces MJ distances for better anomaly detection in time series.
problem Anomaly detection in large collections of time series.
method Introduces semi-metric MJ distances for measuring structural breaks.
result MJ distances outperform existing metrics in detecting similarity and anomalies.
Improved time series forecasting with multivariate probabilistic models.
problem Improving accuracy in forecasting time series with statistical dependencies.
method Conditioned Normalizing Flows for autoregressive deep learning models.
result Improved performance over state-of-the-art models on real-world data sets.
Measuring similarities between unlabeled time series trajectories is an important problem in domains as diverse as medicine, astronomy, finance, and computer vision. It is often unclear what is the appropriate metric to use because of the complex nature of noise in the trajectories (e.g. different sampling rates or out…
Study categorizes time series anomaly detection metrics based on evaluation challenges.
problem Challenges in evaluating time series anomaly detection due to diverse application objectives and metric assumptions.
method Problem-oriented framework categorizing metrics into six dimensions based on evaluation challenges.
result Quantifies each metric's discriminative ability and reveals limitations of widely used metrics.
This study improves estimation of locally stationary functional time series using NW method.
problem Accurately capturing time-dependence in locally stationary functional time series with time-varying covariates.
method Nadaraya-Watson (NW) estimation procedure for the conditional distribution of LSFTS.
result Established convergence rates of NW estimator for LSFTS with respect to Wasserstein distance.
Algorithm classifies market regimes using time series signatures.
problem Classifying different market conditions from time series data.
method Utilizes path signatures and a metric structure for clustering.
result Established a connection between regime separation and point clustering.
Paper introduces novel distances for clustering ordinal time series.
problem Clustering ordinal time series with discrete response.
method Introduces two novel distances and fuzzy clustering algorithms.
result Fuzzy clustering algorithms accurately group series from similar stochastic processes.
FinTSBridge evaluates financial time series models for asset pricing.
problem Lack of effective evaluation methods for financial time series models.
method Developed FinTSBridge suite with new metrics and tasks.
result Showcased new metrics for financial time series models.
EAMDrift improves time series prediction accuracy by 20%.
problem Handling unpredictable patterns in time series data.
method Combines forecasts from multiple individual predictors, retraining models automatically.
result EAMDrift outperforms individual baseline models by 20%.
WF distance measures time series similarity via spectral density displacement.
problem Measuring similarity between time series.
method Wasserstein-Fourier distance between normalised power spectral densities.
result WF establishes as a general-purpose metric for time series.
New scheme detects anomalies in time series data quickly and accurately.
problem Detecting anomalies in time series data with multi-seasonality and unlabeled data.
method Prediction-driven, unsupervised anomaly detection scheme combining decomposition and inference.
result Our scheme outperforms existing algorithms in AUC metric while maintaining efficiency.
Unsupervised learning of time series data, also known as temporal clustering, is a challenging problem in machine learning. Here we propose a novel algorithm, Deep Temporal Clustering (DTC), to naturally integrate dimensionality reduction and temporal clustering into a single end-to-end learning framework, fully unsupe…
This paper improves QoS metric prediction in DTNs using diffusion models.
problem Improving QoS metric prediction in Delay-Tolerant Networks (DTNs) to enhance network performance.
method Formulates QoS metric prediction as a probabilistic forecasting problem on multivariate time series, incorporating latent temporal dynamics.
result The proposed approach outperforms traditional methods in QoS metric prediction for DTNs.
TSGAN models time series data with limited data, outperforming competitors.
problem Lack of quality time series data for machine learning.
method Proposes Time Series GAN (TSGAN) for synthetic time series generation.
result TSGAN outperforms competitors in FID metric and qualitative classification.
Paper proposes counterfactual explanations for ML on multivariate time series data.
problem Lack of user trust and difficulty in debugging ML frameworks using multivariate time series data.
method Proposes a novel explainability technique for providing counterfactual explanations.
result Outperforms state-of-the-art explainability methods in metrics like faithfulness and robustness.
CCE improves anomaly detection metrics by measuring both confidence and consistency.
problem Existing anomaly detection metrics lack discriminative power, hyperparameter dependency, and robustness to perturbations.
method CCE uses Bayesian estimation to quantify uncertainty and constructs global and event-level confidence and consistency scores.
result CCE demonstrates strict boundedness, robustness, and linear time complexity.
Causal analysis predicts market trends using time series data.
problem Predicting financial market trends using diverse time series data.
method Causal analysis based on lagged Pearson correlation applied to financial metrics.
result Discrimination of causal connections between different types of market data.
MADS improves time series imputation performance across real-world datasets.
problem Time series imputation challenges due to variability in data types.
method MADS uses SIRENs for high-fidelity signal reconstruction and a hypernetwork for generalization.
result MADS outperforms state-of-the-art methods on real-world datasets.
New metrics fail adversarial tests, with some more robust than others.
problem Evaluation metrics for time-series anomaly detection were improved but not fully robust.
method Adversarial stress-testing of 12 adopted metrics on real benchmarks.
result Some metrics are more robust than others, with ROC-based metrics being gamed more often.
RENAL test evaluates generative models for time series data.
problem Evaluating generative models for time series data is challenging.
method RENAL test uses recurrent neural networks to transform time series into conditionally independent data pairs for goodness-of-fit testing.
result RENAL test outperforms existing methods in evaluating generative models for time series data.
Proposes MLCNN for better multivariate time series forecasting.
problem Challenges in forecasting multivariate time series, especially the limitation of predicting only one future moment.
method MLCNN, a multi-task deep learning framework inspired by Construal Level Theory, fuses future visions of near and distant future predictions.
result Significant improvements in forecasting accuracy (4.59% RMSE reduction, 6.87% MAE reduction) on real-world datasets.
This paper introduces new invariants for time series analysis.
problem Analyzing the diversity and invariants of time series data.
method Introduces new invariants derived from the continuity of magnitude and maximum diversity.
result Demonstrates improved performance in machine learning experiments with real-world data.
New method uses randomised signatures for generating financial time series data.
problem Generating synthetic financial time series data accurately.
method Introduced a Wasserstein-type distance based on discrete-time randomised signatures.
result Demonstrated universal approximation for randomised signatures on continuous functions.
Proposes a transformer-based approach for anomaly detection in time series data.
problem Inadequate evaluation metrics and inability to capture temporal features in time series anomaly detection.
method Introduces a proper evaluation metric and proposes a transformer-based approach for anomaly detection in time series data.
result Transformer-based approach outperforms state-of-the-art detectors in detecting sequential anomalies.
In this paper we study the generalization capabilities of fully-connected neural networks trained in the context of time series forecasting. Time series do not satisfy the typical assumption in statistical learning theory of the data being i.i.d. samples from some data-generating distribution. We use the input and weig…
Proposes a deep learning model for probabilistic forecasting that is also interpretable.
problem Inability to explain predictions of neural network-based time series forecasting methods.
method Deep Autoregressive Networks (DANLIP) for locally interpretable probabilistic forecasting.
result DANLIP provides interpretable predictions with comparable performance to state-of-the-art methods.
AER combines auto-encoder and LSTM for better time series anomaly detection.
problem Anomaly detection in time series data with limited labeled data and ambiguous definitions.
method AER (Auto-Encoder with Regression) integrates auto-encoder and LSTM for joint predictions and reconstructions.
result AER achieves the highest F1 score across 12 datasets with comparable runtime.
This paper presents a novel time series clustering method, the self-organising eigenspace map (SOEM), based on a generalisation of the well-known self-organising feature map (SOFM). The SOEM operates on the eigenspaces of the embedded covariance structures of time series which are related directly to modes in those tim…
This study compares deep learning models for multi-step dissolved oxygen prediction.
problem Lack of comprehensive comparison among deep learning models for multi-step time series forecasting.
method Walk-forward validation using real-time data from 2012 to 2016, tested models: CNN, TCN, LSTM, GRU, BiRNN.
result GRU outperforms other models in multi-step time series forecasting.