A new algorithm for faster incremental kernel PCA and Nyström approximation.
problem Efficiency in handling streaming data and large datasets.
method Incremental kernel PCA and Nyström approximation using rank one updates.
result More computationally and memory efficient than existing methods.
Deep Incremental Boosting speeds up Deep Learning training with improved generalization.
problem Reducing training time and improving generalization in Deep Learning.
method Inspired by AdaBoost and Transfer Learning, Deep Incremental Boosting adapts Ensemble methods to Deep Learning.
result Reduces training time and improves generalization on Deep Learning datasets.
Paper introduces a new method for learning robot dynamics.
problem Learning robot dynamics with limited prior information.
method Incremental semiparametric inverse dynamics learning combining parametric and nonparametric models.
result Validated the approach on a humanoid robot arm.
The paper extends cluster validity indices for incremental analysis.
problem Providing incremental alternatives for cluster validation.
method Extending iCVI family to include 6 incremental indices and examining their behavior under under- and over-partitioning.
result Over-partitioning is more challenging to detect than under-partitioning.
Dex improves reinforcement learning by solving complex environments incrementally.
problem Training reinforcement learning agents for complex, ever-changing environments.
method Incremental learning approach, using optimal weights from simpler environments.
result Incremental learning yields superior performance across multiple Dex environments.
Paper proposes faster incremental subclass discriminant analysis.
problem Efficiently classify subclasses in incremental data.
method Exact and approximate linear and kernelized solutions.
result Superior training time and accuracy compared to existing methods.
Paper analyzes fast SAGA method for nonconvex optimization problems.
problem Optimizing nonconvex problems of the form minx∑ifi(x) method Incremental aggregated gradient method (SAGA) within an Incremental First-order Oracle framework
result SAGA converges to a stationary point faster than gradient descent and stochastic gradient descent, and at a linear rate to the global optimum for a specific class of nonconvex problems.
Paper tackles few-shot class-incremental learning with a neural gas network.
problem Incrementally learn new classes from very few labelled samples without forgetting old classes.
method Proposes TOPIC framework using a neural gas network to preserve class topology and adapt to new samples.
result Significantly outperforms other methods on CIFAR100, miniImageNet, and CUB200 datasets.
EILearn learns incrementally using previous classifier knowledge.
problem Incremental learning with previous data.
method Retains and uses previous classifier knowledge, monitors performance, eliminates poorly performing classifiers.
result Outperforms existing incremental learning approaches.
A new model learns preferences incrementally without personal data.
problem Incremental session-based recommendation without personal data.
method Memory Augmented Neural model (MAN) that combines a neural recommender with a nonparametric memory.
result MAN consistently outperforms existing methods in incremental session-based recommendation.
Stochastic Gradient Trees learn decision trees incrementally.
problem Learning decision trees using stochastic gradient information.
method Incremental learning setting, soft splits not used, new tree not constructed per update.
result Performs similarly to standard incremental classification trees, outperforms state of the art incremental regression trees, comparable to batch multi-instance learning methods.
CIAG method accelerates optimization for high-dimensional problems.
problem Training classifiers for high-dimensional problems with large datasets.
method CIAG method uses curvature information to accelerate IAG methods.
result Improved linear convergence rate over state-of-the-art IAG methods.
Efficiently updates KRR for big streams with minimal redundant computation.
problem Redundant computation in incremental KRR for big data streams.
method Supports incremental/decremental processing for single and multiple samples, dividing data into batches.
result Significantly reduced computational time without sacrificing accuracy.
Proposes a probabilistic optimization method for large-scale problems.
problem Large-scale regularized optimization problems.
method Develops a probabilistic interpretation of the incremental proximal gradient algorithm and uses Bayesian filtering.
result Makes it possible to solve large-scale problems using well-known Bayesian filters.
A new generative classification strategy outperforms existing methods in class-incremental learning.
problem Incrementally training deep neural networks to recognize new classes is challenging.
method Proposes learning the joint distribution p(x,y) and performing classification using Bayes' rule, implemented with variational autoencoders and importance sampling.
result Performs very well on continual learning benchmarks, outperforming existing baselines.
New algorithm improves on EM for streaming data, outperforming existing methods.
problem Processing high-volume, streaming data efficiently.
method Incremental stochastic Majorization-Minimization (MM) algorithm.
result The algorithm converges to a stationary point with vanishing gradient.
New method combines population and completion tasks in knowledge graphs.
problem Insufficient external resources hinder statistical inference in knowledge graphs.
method Probabilistic factorisation method that uses path structure for both population and completion.
result Balanced exploitation-exploration helps incremental population and improves prediction of missing information.
Develops an efficient method for real-time data analysis and visualization.
problem Challenges of analyzing high-dimensional data.
method Incremental non-linear manifold approximation using GMRA framework.
result Accurately represents non-linear manifolds with small initial samples.
Incremental training method for deep neural networks.
problem Training deep neural networks efficiently and with incremental growth.
method Partitioning the network into sub-networks, gradually incorporating them, and using look-ahead initialization.
result Incremental approach reaches baseline accuracy and identifies smaller network partitions.
Autoencoder reduces memory overhead in incremental class learning.
problem Catastrophic forgetting in continual learning.
method Uses autoencoder to extract prototypes and store mean prototypes per class.
result Comparable performance to state-of-the-art with lower memory cost.
New model LMRC tackles class incremental learning without needing old classes.
problem Softmax suppression problem in class incremental learning.
method Label Mapping with Response Consolidation (LMRC) and multi-head neural network.
result LMRC achieves better performance than related methods in different scenarios.
Proposes a method to adapt to new classes in a domain shift.
problem Learning new classes in a domain shift without labeled supervision.
method Inspired by prototypical networks, the method classifies target samples into shared and novel classes.
result Superior performance compared to DA and CI methods in the CIDA paradigm.
Extend deep neural networks for multiple anatomical structures in real-time.
problem Lack of comprehensive patient-specific anatomical models for complex surgical planning.
method Class-incremental segmentation framework that extends deep networks with minimal incremental annotation.
result Framework retains previous structure segmentation performance and learns new structures without catastrophic forgetting.
A new method for fast incremental/decremental analysis without recursion.
problem Efficiently updating support-vector models with new data.
method Ridge Support Vector Models with Weight-Error Curves (WECs) for recursion-free computation.
result All new Lagrangian multipliers can be computed simultaneously, relaxing previous constraints.
An incremental method for spectral clustering of unknown clusters.
problem Determining the number of clusters in spectral clustering when it is unknown.
method Incremental method leveraging eigenstructure of graph Laplacian matrix.
result Effective eigenpair computation and determining the number of clusters.
New method for clustering large multi-view data.
problem Handling large multi-view data efficiently.
method Incremental minimax optimization based fuzzy clustering (IminimaxFCM).
result IminimaxFCM outperforms related methods in clustering accuracy.
Improved incremental sequence classification with temporal consistency.
problem Updating predictions as new sequence elements are revealed.
method Temporal-difference learning and a temporal-consistency condition for successive predictions.
result Optimizing a novel loss function improves data efficiency and predictive accuracy.
DPTA improves CIL by adapting PTMs with dual prototypes.
problem Catastrophic forgetting in incremental learning with pre-trained models.
method Dual-Prototype Network with Task-wise Adaptation (DPTA).
result DPTA consistently outperforms recent methods by 1\%-5\% on multiple benchmarks.
Meta-learning approach improves object detection on new classes.
problem Deterioration of object detection performance on old classes in incremental settings.
method Meta-learning to reshape model gradients for optimal task adaptation.
result Meta-learning approach outperforms state-of-the-art methods in incremental object detection.
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.
CNAS optimizes neural architectures for class-incremental learning.
problem Capacity saturation in static neural architectures for class-incremental learning.
method CNAS uses reinforcement learning and network transformations to adaptively select architectures.
result CNAS outperforms static architectures and is more efficient.
We introduce incremental variational inference and apply it to latent Dirichlet allocation (LDA). Incremental variational inference is inspired by incremental EM and provides an alternative to stochastic variational inference. Incremental LDA can process massive document collections, does not require to set a learning …
Incremental method for graph Laplacian eigenpairs improves clustering efficiency.
problem Determining the number of clusters in spectral clustering.
method Incremental computation of graph Laplacian eigenpairs.
result Efficiently computes the K-th smallest eigenpair. hi-RF method improves large-scale multi-class data classification with less computational time.
problem Dynamic growth of data and classes poses challenges to traditional classification methods.
method hi-RF is an incremental learning method that replaces or updates trees in random forest adaptively.
result hi-RF achieves comparable precision with significantly reduced computational time.
Paper aims to improve AI's ability to learn new tasks incrementally.
problem Catastrophic Forgetting in AI systems learning multiple tasks simultaneously.
method Analyzed iCaRL method, identified knowledge distillation as key, proposed dynamic threshold moving algorithm.
result Demonstrated effectiveness of dynamic threshold moving algorithm on CIFAR100 and MNIST datasets.
Paper tackles catastrophic forgetting in incremental learning with improved cosine distance and PEDCC-Loss.
problem Tackles catastrophic forgetting in incremental learning.
method Ensemble method based on cosine distance and PEDCC-Loss.
result Outperforms recent methods in preserving old knowledge while learning new classes.
Incremental ELMVIS learns from large, unorganized datasets.
problem Learning dependencies from unstructured data.
method Iteratively selects best fitting data samples, adding to the model.
result Capable of learning from non-organized, large datasets.
New method estimates sparse mean from noisy data without knowing sparsity level.
problem Sparse mean estimation under adversarial corruptions.
method Incremental learning approach to nonconvex optimization.
result Achieves optimal statistical rate under moderate signal-to-noise ratio.
Proposes MEDIC to improve incremental learning by preventing forgetting and intransigence.
problem Challenges of forgetting old knowledge and intransigence on new knowledge in incremental learning.
method Maximum Entropy Regularizer (MER) and DropOut Sampling (DOS) to penalize uncertain knowledge and reduce class imbalance.
result Proposed method 'MEDIC' outperforms state-of-the-art algorithms in accuracy, forgetting, and intransigence.
Best-choice edge grafting speeds up MRF structure learning.
problem Efficiently learning the structure of Markov random fields (MRFs) in a scalable manner.
method Incremental, structured approach that activates edges in groups of features.
result Significant speedup in structure learning with a controllable trade-off between speed and quality.
OpenHAIV integrates OOD detection and incremental learning for open-world models.
problem Challenges in open-world recognition, especially in model knowledge updates and OOD detection.
method Unified pipeline combining OOD detection, new class discovery, and incremental fine-tuning.
result Models can autonomously acquire and update knowledge in open-world environments.
Automatically identifies vehicles from audio sensors without needing labeled data.
problem Vehicle recognition and classification from acoustic signals.
method Incremental reseeding of acoustic signatures using spectral embedding and clustering.
result Incremental reseeding accurately identifies individual vehicles from their acoustic signatures.
Method estimates causal effects from incremental data, overcoming missing data challenges.
problem Estimating causal effects from non-stationary, incrementally available observational data.
method Continual Causal Effect Representation Learning
result Method achieves continual causal effect estimation without compromising original data.
Paper improves convergence rates and step sizes for gradient algorithms.
problem Limited convergence rates and step sizes in existing algorithms.
method General proximal incremental aggregated gradient algorithm.
result Better and novel convergence results under general scheme.
TKIL improves class-balanced performance in incremental learning.
problem Catastrophic forgetting in sequential learning tasks.
method Introduces Tangent Kernel for Incremental Learning (TKIL) based on Neural Tangent Kernel (NTK).
result TKIL achieves better overall accuracy and variance across classes.
SupportNet tackles catastrophic forgetting in incremental learning with support data.
problem Catastrophic forgetting in deep learning models when learning new data.
method SupportNet combines deep learning and SVM to identify support data, which are used to reinforce old data knowledge.
result SupportNet outperforms state-of-the-art methods and matches deep learning models trained from scratch on both old and new data.
Method predicts LFSM increments from past observations using codifference.
problem Forecasting LFSM increments from discrete-time observations.
method Uses codifference for serial dependence, with conditional expectation or projection for α>1 or α<2. result Method shows promising performance in forecasting volatilities, capturing kurtosis and serial dependence.
Incremental machine learning models predict COVID-19 cases more efficiently than traditional methods.
problem Predicting the spread of COVID-19 cases in real-time across multiple countries.
method Comparison of online incremental machine learning algorithms against traditional LSTM models.
result Incremental machine learning models are more efficient and computationally cheaper than traditional methods.