A new method detects anomalies in multivariate streams without unit dependence.
problem Detect anomalies in multivariate streams without unit dependence.
method Proposes SigMahaKNN combining variance norm and path signature.
result SigMahaKNN detects anomalies better than existing methods.
PySAD offers a unified Python framework for efficient streaming anomaly detection.
problem Efficient anomaly detection in streaming data with strict constraints.
method Unified architecture with 17+ streaming algorithms, specialized components, and support for multiple learning paradigms.
result PySAD enables real-time processing with bounded memory and is compatible with other Python frameworks.
In this paper we propose a computationally efficient algorithm for on-line variable selection in multivariate regression problems involving high dimensional data streams. The algorithm recursively extracts all the latent factors of a partial least squares solution and selects the most important variables for each facto…
KQT-EWMA monitors multivariate data streams online with flexible and practical change detection.
problem Online monitoring of multivariate data streams for detecting changes.
method Combines Kernel-QuantTree histogram and EWMA statistic for non-parametric monitoring.
result Controls Average Run Length (ARL0) while achieving comparable detection delays.
Develops new techniques for learning from sequential data groups.
problem Learning from groups of inputs rather than individual inputs.
method Introduces feature-based and kernel-based learning techniques for sequential data.
result Achieves state-of-the-art performance on various real-world examples.
The study examines how bias affects hypothesis formation in neural networks.
problem Characterizing the impact of bias on hypothesis formation in neural networks.
method An automated data-driven projection pursuit neural network to extract and select features for binary classification.
result The refinement of a working hypothesis converges to a robust multivariate perception of data.
Paper tackles class-incremental time series classification with dual-stream feature extraction.
problem Class-incremental continual learning for multivariate time series data.
method Dual-stream feature extraction pipeline combining deep temporal embedding features and statistical features.
result Competitive average accuracy across multiple datasets with low forgetting rates.
In recent years, there has been a growing interest in identifying anomalous structure within multivariate data streams. We consider the problem of detecting collective anomalies, corresponding to intervals where one or more of the data streams behaves anomalously. We first develop a test for a single collective anomaly…
The concept of SCN offers a fast framework with universal approximation guarantee for lifelong learning of non-stationary data streams. Its adaptive scope selection property enables for proper random generation of hidden unit parameters advancing conventional randomized approaches constrained with a fixed scope of rand…
Proposes a multi-stream RNN model for predicting merchant transactions.
problem Predicting future transaction statistics of merchants.
method Multi-stream RNN model tailored for multivariate time series and multi-step predictions.
result Outperforms existing state-of-the-art methods in merchant transaction predictions.
Many events occur in the world. Some event types are stochastically excited or inhibited---in the sense of having their probabilities elevated or decreased---by patterns in the sequence of previous events. Discovering such patterns can help us predict which type of event will happen next and when. We model streams of d…
A streaming algorithm estimates quadratic covariation from financial data efficiently.
problem Estimating quadratic covariation from ultra-high-frequency financial data with limited memory.
method Formulated multi-scale, realized kernel, pre-averaging, and modulated realized covariance estimators with fixed bandwidth.
result Fixed bandwidth estimators require higher bandwidth for positive semidefiniteness.
STVNN models spatiotemporal data using covariance matrices.
problem Challenges in modeling spatiotemporal interactions in multivariate time series.
method Introduces SpatioTemporal coVariance Neural Network (STVNN) that operates on sample covariance matrix and uses joint spatiotemporal convolutions.
result STVNN is stable to online estimation uncertainties and outperforms temporal PCA.
Sequential or online dimensional reduction is of interests due to the explosion of streaming data based applications and the requirement of adaptive statistical modeling, in many emerging fields, such as the modeling of energy end-use profile. Principal Component Analysis (PCA), is the classical way of dimensional redu…
Online change detection algorithm using random Fourier features.
problem Online non-parametric change point detection in multivariate data streams.
method Sequential testing procedure based on random Fourier features.
result The algorithm has optimal detection delay in the minimax sense.
A federated model predicts failures using multi-stream incomplete data.
problem Insufficient data for reliable prognostic models in multi-stream applications.
method Federated data fusion, multivariate functional principal component analysis, (log)-location-scale regression model, federated algorithm.
result Performance is as good as classic non-federated models and better than individual models.
Proposes a model for predicting events from event streams.
problem Predicting events like part replacement and failure in manufacturing and teleservice systems.
method Non-parametric prognostic framework using MGCP modulated Poisson processes.
result MGCP prior facilitates sharing of information and analysis of flexible event patterns.
The paper monitors artificial neural networks using embeddings and multivariate control charts.
problem Ensuring the stability of artificial neural networks during deployment.
method Monitoring the latent feature representation (embedding) of ANN outputs using multivariate control charts based on data depth and ranks.
result The proposed method effectively detects nonstationary data streams in ANN outputs.
Graph representations offer powerful and intuitive ways to describe data in a multitude of application domains. Here, we consider stochastic processes generating graphs and propose a methodology for detecting changes in stationarity of such processes. The methodology is general and considers a process generating attrib…
Estimating the dependency of variables is a fundamental task in data analysis. Identifying the relevant attributes in databases leads to better data understanding and also improves the performance of learning algorithms, both in terms of runtime and quality. In data streams, dependency monitoring provides key insights …
Develops a framework for inferring causal relationships in networked data with uncertainty quantification.
problem Extracting reliable inference from complex Hawkes network data with uncertainty.
method Statistical inference framework based on maximum likelihood estimation and concentration inequalities of continuous-time martingales.
result Provides a non-asymptotic confidence set for uncertainty quantification.
BayOTIDE tackles imputation of irregularly sampled multivariate time series with uncertainty quantification.
problem Imputation of irregularly sampled multivariate time series with missing values and noises.
method BayOTIDE treats multivariate time series as a combination of low-rank temporal factors with different patterns, using Gaussian Processes (GPs) as functional priors and converting them into state-space priors for scalable online inference.
result BayOTIDE can handle imputation over arbitrary time stamps and offers uncertainty quantification and interpretability.
Study examines how different time series cross-validation methods affect anomaly detection in multivariate time series.
problem Evaluating anomaly detection in multivariate time series requires preserving temporal dependencies, especially for subsequence anomalies.
method Systematically investigates walk-forward and sliding window methods across various validation configurations and classifier types.
result Sliding window method consistently yields higher precision-recall scores and reduced fold-to-fold performance variance, particularly for deep learning models.
RG-TTA adapts neural forecasters to streaming time series shifts by modulating adaptation intensity.
problem Adapting neural forecasters to distribution shifts in streaming time series data.
method RG-TTA uses a meta-controller that continuously modulates adaptation intensity based on distributional similarity.
result RG-TTA achieves the lowest MSE in 156 of 224 seed-averaged experiments, reducing MSE by 5.7% vs TTA.
The paper optimizes sensor selection for network time series data.
problem Optimizing sensor selection for network time series data with minimal error.
method Data-driven strategies to turn off sensors or select a sampling set of nodes.
result Proposes and compares various data-driven strategies for sensor selection.
A new method for estimating SW from streaming data.
problem Estimating Wasserstein distance from sample streams.
method Introducing a streaming estimator of the 1DW and applying it to all projections.
result Stream-SW achieves more accurate approximation of SW than random subsampling.
Data stream classification methods demonstrate promising performance on a single data stream by exploring the cohesion in the data stream. However, multiple data streams that involve several correlated data streams are common in many practical scenarios, which can be viewed as multi-task data streams. Instead of handli…
The prevalence of networked sensors and actuators in many real-world systems such as smart buildings, factories, power plants, and data centers generate substantial amounts of multivariate time series data for these systems. The rich sensor data can be continuously monitored for intrusion events through anomaly detecti…
New method detects changes in high-dimensional data from small samples.
problem Detecting changes in high-dimensional data with limited samples.
method Angular kernel scan framework for detecting marginal distributional shifts.
result Exact population mean factorization and asymptotically distribution-free test.
Data stream clustering tackles real-time data processing challenges.
problem Real-time processing of data streams with less prior information.
method Review of data stream clustering algorithms and their characteristics.
result Comparison and analysis of data stream clustering algorithms.
Bayesian analysis of financial time series using R-INLA.
problem Analyzing interdependencies between stock volatility measures.
method Flexible level correlated model (LCM) with INLA approximation.
result Fast approximate Bayesian modeling of positive-valued time series.
Bayesian tensor train method recovers streaming data with high accuracy.
problem Recovering high-order, incomplete, and noisy streaming data.
method Bayesian tensor train decomposition using streaming variational Bayes method.
result The proposed SPTT algorithm excels in recovering streaming data compared to state-of-the-art methods.
While the volume of electronic health records (EHR) data continues to grow, it remains rare for hospital systems to capture dense physiological data streams, even in the data-rich intensive care unit setting. Instead, typical EHR records consist of sparse and irregularly observed multivariate time series, which are wel…
New metrics needed for streaming ML due to delayed labels.
problem Streaming ML evaluation fails to identify unexpected performance.
method Recommend additional metrics for streaming ML performance.
result New metrics are needed for streaming ML due to delayed labels.
stream-learn is a Python package compatible with scikit-learn and developed for the drifting and imbalanced data stream analysis. Its main component is a stream generator, which allows to produce a synthetic data stream that may incorporate each of the three main concept drift types (i.e. sudden, gradual and incrementa…
Nowadays, every device connected to the Internet generates an ever-growing stream of data (formally, unbounded). Machine Learning on unbounded data streams is a grand challenge due to its resource constraints. In fact, standard machine learning techniques are not able to deal with data whose statistics is subject to gr…
CROC identifies the earliest-changing stream as the root cause in multi-stream data.
problem Distribution-free root cause analysis in multi-stream data with unknown distributional changes.
method Conformal p-values and finite-sample valid confidence sets.
result CROC efficiently isolates the root cause under minimal assumptions.
SDF adapts Deep Forest for evolving data streams with active learning.
problem Adapting Deep Forest for evolving data streams.
method Streaming Deep Forest (SDF) with Augmented Variable Uncertainty (AVU) active learning.
result SDF with AVU outperforms other methods trained with all instances by 70% labeling budget.
Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams.
problem Financial fraud detection in digital banking requires reasoning over multiple heterogeneous event streams.
method Multi-Stream Fraud Transformer (MSFT) architecture that encodes each event stream with independent Transformer encoders and fuses their representations through configurable mechanisms.
result Sequence models significantly outperform gradient-boosted trees operating on aggregated features.
A privacy-preserving framework detects faults in circular economy processes.
problem Lack of shared data across company borders due to privacy concerns.
method Federated Principal Component Analysis (PCA) and Secure Multiparty Computation.
result The proposed FedMSPC framework outperforms standard PCA in fault detection.
Dynamic Model Tree improves online learning for evolving data streams.
problem Effective and transparent machine learning on data streams is challenging.
method Revisit Model Trees for data stream applications, introducing Dynamic Model Tree.
result Dynamic Model Tree reduces the number of splits and outperforms state-of-the-art models.
Streaming algorithms are generally judged by the quality of their solution, memory footprint, and computational complexity. In this paper, we study the problem of maximizing a monotone submodular function in the streaming setting with a cardinality constraint k. We first propose Sieve-Streaming++, which requires just…
Unified study of stateful replay for streaming learning, reducing forgetting by 2-3x.
problem Catastrophic forgetting in streaming generative and predictive learning.
method Unified analysis of stateful replay for autoencoding, forecasting, and classification tasks.
result Stateful replay reduces average forgetting by a factor of 2-3 on heterogeneous multi-task streams.
Low-precision streaming PCA estimates the leading eigenvector with limited precision.
problem Estimating the leading eigenvector in a streaming setting with limited precision.
method Oja's algorithm with linear and nonlinear stochastic quantization.
result A batched version of the quantized variants achieves the lower bound on quantization error up to logarithmic factors.
Scikit-multiflow is a multi-output/multi-label and stream data mining framework for the Python programming language. Conceived to serve as a platform to encourage democratization of stream learning research, it provides multiple state of the art methods for stream learning, stream generators and evaluators. scikit-mult…
We introduce a new sub-linear space sketch---the Weight-Median Sketch---for learning compressed linear classifiers over data streams while supporting the efficient recovery of large-magnitude weights in the model. This enables memory-limited execution of several statistical analyses over streams, including online featu…
New robustness certificates for streaming models with a sliding window.
problem Applying robustness certificates to streaming data with correlated inputs.
method Deriving robustness certificates for models using a sliding window over a sequence of potentially correlated inputs.
result Guarantees hold for the average model performance across the entire stream, independent of stream size.
Convolutional neural networks outperform other architectures in streaming time series classification.
problem Efficient deep learning models for real-time data streams.
method Asynchronous dual-pipeline deep learning framework for real-time predictions.
result Convolutional architectures achieve higher accuracy and efficiency in streaming time series classification.