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.
A new method for online multi-label stream classification.
problem Challenges in classifying continuous data streams with concept drift and delayed labels.
method Online unsupervised incremental method based on self-organizing maps.
result The method is highly competitive in both stationary and concept drift scenarios.
GOOWE-ML ensemble improves multi-label stream classification.
problem Online multi-label data stream classification.
method Novel online stacked ensemble with spatial weighting.
result GOOWE-ML ensembles outperform other models in predictive performance.
Scikit-multiflow is a Python framework for multi-output/stream data mining.
problem Handling multi-output/stream data efficiently.
method Multi-output/multi-label stream data mining framework with state-of-the-art methods.
result Enables democratization of stream learning research.
Survey of active learning for data streams.
problem Efficiently labeling data points in real-time data streams.
method Review of active learning approaches for data streams.
result Overview of recent approaches for online active learning.
Optimal streaming algorithm for crowdsourced binary classification.
problem Binary classification of data using crowdsourcing.
method Learning labeller competence and minimizing prediction error rate.
result Cumulative regret is finite and independent of the number of tasks.
Paper tackles active labeling for partial supervision.
problem Accessing stochastic gradients with partial supervision.
method Streaming technique to minimize generalization error.
result Proves minimization of generalization error ratio.
FASE-AL uses active learning to reduce labeling costs for data streams.
problem Reduction of labeling costs for data stream classification.
method Combines Fast Adaptive Stacking of Ensembles (FASE) with active learning.
result Achieves high accuracy with minimal labeled data.
SLL models labels as they arrive, improving classification performance.
problem Handling dynamic multi-label learning environments with changing labels.
method Label self-representation and two-step approach: regression and ERM.
result SLL generates tighter generalization error bounds for new labels.
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.
New approach for feature evolution in streaming data with limited storage.
problem Rarely-provided labels in feature evolving streams.
method Incorporates manifold regularization and a buffer to adapt to different storage budgets.
result Preserves the performance of feature evolving learning across different storage budgets.
New method tackles dynamic data labeling issues with limited labels.
problem Dynamic data labeling with scarce labeled instances.
method Instance exploitation technique for aggressive model adaptation.
result Aggressive model adaptation leads to better performance than standard methods.
QActor optimizes learning from noisy labeled data streams by querying experts for clean labels.
problem Learning from noisy labeled data in continuous streams with limited oracle queries.
method Combines quality models for filtering and oracle queries for true labels, dynamically adjusting query limits.
result QActor nearly matches optimal accuracy with up to 6% additional ground truth data from experts.
Confidence intervals improve decision tree accuracy in streaming data.
problem Improving decision tree accuracy in streaming data with confidence intervals.
method Deriving accurate confidence intervals for decision tree splitting criteria and extending to selective sampling.
result Confidence intervals enhance decision tree accuracy and reduce labeling costs.
ATL learns from many streaming processes without labeled data.
problem Knowledge transfer across many streaming processes with covariate shift and drifts.
method Autonomous transfer learning with generative and discriminative phases, KL divergence optimization, and elastic network structure.
result Improved performance and faster training speed compared to existing methods.
ParsNet tackles weakly supervised data streams with a self-evolving deep neural network.
problem Weakly supervised data streams hinder existing data stream algorithms.
method ParsNet uses a self-labelling strategy with hedge (SLASH) and a closed-loop configuration of generative and discriminative training processes.
result ParsNet outperforms other methods in high-dimensional data streams and infinite delay simulations.
End-to-end learning for robot grasping using image data.
problem Robotic grasping using only monocular images.
method Two-stream architecture: ventral stream for object detection and classification, dorsal stream for grasp planning.
result End-to-end trained model outperforms non-end-to-end systems.
New method for recognizing human activities from streaming videos.
problem Scalable, incremental learning for human activity recognition.
method Incremental learning with active learning strategy.
result Outperforms existing methods in accuracy and model size.
An active learner chooses which data points to label to minimize cost and error in streaming data.
problem Efficiently labeling streaming data points with limited labeling costs.
method Formalizes the problem with a loss function, designs an algorithm with a time and cost dependent threshold, and provides upper and lower bounds.
result The algorithm achieves a worst-case upper bound of O ~ ( B 1 3 K 1 3 T 2 3 ) \widetilde{O}(B^{\frac{1}{3}} K^{\frac{1}{3}} T^{\frac{2}{3}}) O ( B 3 1 K 3 1 T 3 2 ) on the loss after T T T rounds. Memory augmented neural networks improve active learning for one-shot predictions.
problem Scarcity and cost of labeled training data in deep architectures.
method Memory augmented neural networks and Class Margin Sampling (CMS) for reinforcement learning.
result The proposed method outperforms existing baselines in label predictions and reduces label requests.
A new framework detects novel classes in data streams.
problem Detecting novel class labels in data streams.
method Semi-supervised multi-task learning framework for co-representation learning.
result Superior performance over existing methods on real-world datasets.
Paper proposes a semi-supervised method for detecting concept drift in streaming environments.
problem Detecting concept drift in streaming environments with limited labeled data.
method Utilizes density estimation of posterior probabilities in partially labeled streaming data.
result Demonstrates superior concept drift detection in streaming environments with limited labeled data.
New algorithm robust to label corruptions in active learning.
problem Active learning under unknown adversarial label corruptions.
method Proposed a new active learning algorithm that is provably correct without assumptions on corruptions.
result Achieves minimax label complexity in non-corrupted setting and only requires additional labels to achieve desired accuracy in corrupted setting.
New algorithm reduces label queries in online learning with bounded errors.
problem Minimizing label queries while limiting prediction errors in streaming data.
method Disagreement-based online learning algorithm for a general hypothesis space under Tsybakov noise.
result The proposed algorithm achieves an optimal label complexity of O ( d T 2 − 2 α 2 − α log 2 T ) O(dT^{\frac{2-2α}{2-α}}\log^2 T) O ( d T 2 − α 2 − 2 α log 2 T ) with a matching lower bound. New method combines deep learning and streaming learning for better incremental learning.
problem Catastrophic forgetting in deep neural networks when updated incrementally.
method Combining streaming linear discriminant analysis with deep learning.
result Outperforms incremental batch learning and streaming learning on ImageNet and CORe50.
A deep network learns diverse contexts from multi-modal sensor data.
problem Recognizing diverse contexts and activities from multi-modal sensor data.
method Multi-stream temporal convolutional network with contextualization module.
result Deep network achieves optimal recognition rate.
Paper classifies multiple video sources in encrypted tunnels using NLP-inspired features.
problem Traffic classification in encrypted video streams.
method Deep learning with a novel NLP-inspired feature for multi-label classification.
result The method achieves high performance on binary and multilabel classification tasks.
A new method detects concept drift without true labels.
problem Detecting concept drift in unsupervised settings.
method Student-teacher learning paradigm for drift detection.
result The method outperforms state-of-the-art approaches in experiments.
SAMM monitors model drift in data streams without labels.
problem Detecting concept drift in unsupervised data streams.
method Time and space efficient unsupervised streaming algorithm for drift detection; generates explanations for drift.
result SAMM detects useful anomalous events for fraud detection.
Novel semi-supervised method for online structure learning in noisy data streams.
problem Discovering complex relations in noisy data streams with limited labelled data.
method Combines graph-cut minimization and first-order logic for online, single-pass label completion.
result Improves accuracy of structure learning system by completing missing labels.
ABACOC algorithm improves nonparametric data stream classification.
problem Scalable, incremental, nonparametric classification of dynamic data streams.
method Local classifiers dynamically adapt to local complexity.
result State-of-the-art accuracy with strict model size constraints.
Paper explores active learning strategies for real-time credit card fraud detection.
problem Challenges in labeling and imbalanced transaction data for real-time fraud detection.
method Investigates active learning strategies for querying unlabeled transactions, comparing supervised, semi-supervised, and unsupervised approaches.
result Highlights an exploitation/exploration trade-off for active learning in fraud detection.
Active learning tackles cold start and imbalanced data issues.
problem Cold start problem and imbalanced data in ML models.
method ODAL approach with 3-stage AL policies.
result ODAL can quickly reach high performance models with limited labels.
A new method uses active learning to monitor industrial processes more accurately.
problem Classifying process states (IC, OC) with limited labeled data.
method Stream-based active learning for partially hidden Markov models.
result Improved dynamic recognition of process states, especially unseen classes.
We consider the problem of learning convex aggregation of models, that is as good as the best convex aggregation, for the binary classification problem. Working in the stream based active learning setting, where the active learner has to make a decision on-the-fly, if it wants to query for the label of the point curren…
LdSM builds efficient multi-label decision trees with logarithmic depth.
problem Efficiently annotate data points with relevant subsets of labels from a large label set.
method Develops LdSM algorithm for multi-label decision trees with logarithmic depth, optimizing a novel objective function for balanced splits and high class purity.
result Minimizing the proposed objective function leads to pure and balanced data splits, achieving high prediction accuracy and low prediction time.
This work tackles continual learning with semi-supervised data, showing that even with minimal labeled data, performance can match full-supervised methods.
problem Training deep networks on a stream of tasks without forgetting, especially when labeled data is scarce.
method Designing a novel CSSL method that leverages metric learning and consistency regularization to learn from both labeled and unlabeled data.
result Our method outperforms state-of-the-art methods trained with full supervision, achieving comparable performance with only 25% labeled data.
New framework detects adversarial concept drift in streaming data.
problem Adversarial concept drift in dynamic environments.
method Predict-Detect streaming framework for unsupervised drift detection and recovery.
result Framework detects adversarial drift with <6% labeled data, improving active learning for imbalanced data.
DBULL learns new clusters without forgetting past knowledge in streaming unlabelled data.
problem Challenges in Unsupervised Lifelong Learning with evolving data distributions and class labels.
method Bayesian framework for incremental learning, Deep Bayesian Unsupervised Lifelong Learning (DBULL) algorithm, knowledge preservation mechanism, automatic cluster discovery.
result DBULL can progressively discover new clusters without forgetting past knowledge in unlabelled data.
Research explores unsupervised methods for detecting vessel behavior changes in real-time data streams.
problem Detecting shifts in vessel behavior for maritime traffic monitoring.
method Investigates unsupervised and semi-supervised change detection methods.
result Identifies shifts in vessel behavior for unusual events detection.
Meta-learning framework for few-shot one-class classification using order-equivariant networks.
problem Few labeled examples for positive class in one-class classification tasks.
method Order-equivariant networks for meta-learning a binary classifier conditioned on positive examples.
result Meta-learning framework outperforms baselines on unseen synthetic streams.
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.
Paper improves anomaly detection using tree-based ensembles with active learning.
problem Configuring anomaly detectors with true labels to minimize false positives.
method Develops batch and streaming active learning algorithms for tree-based ensembles.
result Significantly more anomalies discovered with active learning compared to baselines.
Active learning improves anomaly detection by tuning ensembles with true labels.
problem Configuring anomaly detectors for minimal effort on false positives.
method Compact description, data drift detection, active learning strategies.
result Active learning significantly improves anomaly discovery and adapts to streaming data.
Approach to detect and adapt to concept drift in unlabeled streaming data.
problem Detect and adapt to concept drift in high-dimensional, noisy, low-context data.
method Density-based clustering for virtual drift and weak supervision for real drift.
result 90% precision in detecting and adapting to concept drift for 4 years after initial deployment.
Designs an online selective sampling approach for choosing which model to use.
problem Active model selection for pre-trained classifiers in unlabeled data streams.
method Online selective sampling approach to query and label examples.
result High probability of outputting the best model with minimal label queries.
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.
Semantic Scan detects subtle, localized events in text streams.
problem Detecting emerging topics in text streams with high accuracy and speed.
method Contrastive topic modeling, online document assignment, spatial scanning.
result Semantic Scan outperforms other methods in detecting anomalous events.