We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another replay-based continual learning paradigm (which we term "marginal rep…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “replay-based continual learning”
CLOPS improves deep learning for continuous physiological data.
problem Deep learning struggles with streaming, multi-sensor clinical data.
method CLOPS is a replay-based continual learning strategy.
result CLOPS outperforms state-of-the-art methods in continual learning scenarios.
D-CBRS manages memory for continual learning by accounting for intra-class diversity.
problem Forgetting in continual learning, especially with class-imbalanced data.
method D-CBRS introduces a novel approach to store instances in memory, considering intra-class diversity.
result D-CBRS outperforms existing methods on data sets with intra-class diversity.
Paper proposes a new method to select memory data for online class-incremental learning.
problem Selecting which buffered images to replay for online class-incremental learning.
method Adversarial Shapley value scoring method to preserve latent decision boundaries.
result Proposed ASER method provides competitive or improved performance compared to state-of-the-art methods.
Develops a framework for continual learning in anomaly detection.
problem Deterioration of monitoring performance due to new defect categories.
method Pseudo replay-based class incremental learning with oversampling.
result Enhanced monitoring performance and flexibility in model architecture.
We examine the question of when and how parametric models are most useful in reinforcement learning. In particular, we look at commonalities and differences between parametric models and experience replay. Replay-based learning algorithms share important traits with model-based approaches, including the ability to plan…
La-MAML improves fast online continual learning with a look-ahead approach.
problem Fast online continual learning with limited model capacity.
method Optimisation-based meta-learning with look-ahead and episodic memory.
result Superior performance on visual classification benchmarks.
This research tackles imbalanced continual learning with a new sampling strategy.
problem Long-tailed distribution in multi-label datasets.
method Partitioning Reservoir Sampling (PRS) for balanced knowledge of head and tail classes.
result The proposed PRS strategy maintains a balanced knowledge of both head and tail classes.
CAM-GAN improves GANs for continual learning with efficient feature map transformations.
problem Efficient continual learning for GANs with reduced parameter growth.
method Designing and leveraging parameter-efficient feature map transformations, including global and task-specific parameters, residual bias, and Fisher information matrix.
result Significantly improved model performance and high-quality samples with fewer parameters.
ER-GNN uses experience replay to prevent GNNs from forgetting previous tasks.
problem Catastrophic forgetting in GNNs when learning multiple tasks sequentially.
method Experience Replay framework to store and replay knowledge from previous tasks.
result ER-GNN effectively mitigates catastrophic forgetting in GNNs.
Neural network tackles continual learning with neuromodulation and local error signals.
problem Catastrophic forgetting in continuous learning.
method Biologically-inspired neural architecture with local learning and neuromodulation, combined with transfer metalearning.
result Superior performance in continual learning tasks compared to other approaches.
This project combines recent advances in experience replay techniques, namely, Combined Experience Replay (CER), Prioritized Experience Replay (PER), and Hindsight Experience Replay (HER). We show the results of combinations of these techniques with DDPG and DQN methods. CER always adds the most recent experience to th…
Modern deep reinforcement learning methods have departed from the incremental learning required for eligibility traces, rendering the implementation of the -return difficult in this context. In particular, off-policy methods that utilize experience replay remain problematic because their random sampling of minibatch…
The paper improves reinforcement learning stability and efficiency with a new theoretical framework.
problem Stability and efficiency in reinforcement learning, especially in data-scarce scenarios.
method Theoretical framework using resampled - and -statistics to model experience replay, applied to policy evaluation and kernel ridge regression.
result Significant improvements in stability and efficiency, particularly in data-scarce scenarios.
SynthER uses generative models to augment limited RL experience.
problem Limited data for reinforcement learning agents.
method SynthER leverages diffusion models to generate synthetic experience data.
result SynthER significantly improves sample efficiency and training of RL agents.
Bilevel Continual Learning improves continual learning by transferring knowledge effectively.
problem Catastrophic forgetting and poor generalization in continual learning.
method Bilevel optimization and dual memory management strategies.
result BCL achieves effective knowledge transfer and alleviates catastrophic forgetting.
EBMs improve continual learning without external memory or regularization.
problem Improving continual learning without external memory or regularization.
method Energy-Based Models with contrastive divergence training objective.
result EBMs outperform baseline methods on various benchmarks.
Proposes a framework for semi-supervised continual learning from sequentially arriving data.
problem Learning from data with changing task distribution over time, especially in domains with a mix of labeled and unlabeled data.
method Meta-Consolidation for Continual Semi-Supervised Learning (MCSSL) framework with a hypernetwork and semi-supervised auxiliary classifier.
result Significant improvements in continual semi-supervised learning setting.
This paper presents a method to improve continual learning stability and plasticity.
problem Balancing learning stability and plasticity in deep learning.
method Batch-level Experience Replay with Review approach.
result Achieved 1st place in all three scenarios of the CVPR 2020 CLVision challenge.
Study on continual learning with Twitter data, developing ConGraD algorithm.
problem Personalized online language learning on a massive scale.
method Developed POLL problem setting, collected Firehose datasets, and introduced ConGraD algorithm.
result ConGraD algorithm outperforms prior continual learning methods on Firehose datasets.
Bayesian approach helps update deep models without forgetting past data.
problem Updating deep models sequentially without forgetting past data.
method Bayesian inference for continual learning.
result Bayesian approach enables updating model beliefs with new data.
Faster policy learning via continuous-time gradients.
problem Efficiently estimating policy gradients for continuous-time systems.
method Approximating continuous-time gradients directly, using adaptive discretization.
result More efficient policy gradient estimator leads to faster learning.
New method tackles anomaly detection in video surveillance using continual learning.
problem Challenges in continual learning for high-dimensional applications like video surveillance.
method Transfer learning and continual learning for online anomaly detection.
result Significantly reduces training complexity and continual learning from recent data.
Continual learning is hard for AI, leading to forgetting old knowledge.
problem Catastrophic forgetting in AI when learning new data.
method Review of continual learning in deep learning.
result Challenges and insights in continual learning.
Improves continual learning with theoretical guarantees and a new algorithm.
problem Learning incremental tasks with dynamic data distributions.
method Contrastive and distillation losses with theoretical performance guarantees.
result Theoretical performance bounds and improved continual learning performance.
Paper proposes SDRL to improve continual learning with less computational cost.
problem Catastrophic forgetting in continual learning.
method SDRL method that refines gradients from memorized samples to reduce gradient diversity.
result SDRL shows better performance than state-of-the-art methods on multiple benchmark tasks.
Study shows memory needs grow with task sequence length in continual learning.
problem Challenges in retaining aptitude for multiple learning tasks sequentially.
method Complexity-theoretic study using communication complexity and multiplicative weights update.
result Memory needs grow linearly with task sequence length, suggesting intractability.
Paper analyzes convergence of continual learning with adaptive methods.
problem Preventing catastrophic forgetting in sequential learning tasks.
method Adaptive method for nonconvex continual learning (NCCL) adjusts step sizes of previous and current tasks.
result Proposed adaptive method achieves same convergence rate as SGD when catastrophic forgetting is suppressed.
Experiments used in current continual learning research do not faithfully assess fundamental challenges of learning continually. Instead of assessing performance on challenging and representative experiment designs, recent research has focused on increased dataset difficulty, while still using flawed experiment set-ups…
OGD proves robustness to Catastrophic Forgetting in Continual Learning.
problem Catastrophic Forgetting in Continual Learning with deep neural networks.
method Theoretical framework based on Neural Tangent Kernel for OGD.
result First generalization bound for SGD and OGD in Continual Learning.
RSAC improves lightweight continuous learning efficiency.
problem Excessive training time and memory usage in continuous learning.
method Regularized subspace approximation classifier with feature reduction and regularization.
result RSAC achieves more efficient continuous learning than prior methods.
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in compl…
Develops DPG methods for continuous-time RL with deterministic policies.
problem High variance and slow convergence in stochastic policy RL methods.
method Derives continuous-time policy gradient formula and proposes CT-DDPG algorithm.
result CT-DDPG achieves superior stability and faster convergence in continuous-time RL.
Residual Continual Learning prevents forgetting in sequential tasks.
problem Preventing catastrophic forgetting in sequential learning of multiple tasks.
method ResCL reparameterizes network parameters by combining original and fine-tuned networks, keeping network size constant.
result ResCL achieves state-of-the-art performance in various continual learning scenarios.
Research shows continual learning challenges in confounded datasets.
problem Challenges in mitigating confounders in continual learning settings.
method Formal description of continual confounders, construction of ConCon dataset.
result Standard continual learning methods fail to ignore confounders.
A new framework for federated continual learning reduces interference and improves performance.
problem Learning from a sequence of tasks with limited data from each client.
method Federated Weighted Inter-client Transfer (FedWeIT) framework.
result FedWeIT significantly outperforms existing methods with reduced communication cost.
ORDisCo learns from unlabeled data to improve semi-supervised continual learning.
problem Lack of effective use of unlabeled data in semi-supervised continual learning.
method Deep Online Replay with Discriminator Consistency (ORDisCo) that continually passes the learned data distribution to a classifier and selectively stabilizes discriminator parameters.
result Significant performance improvement on various semi-supervised learning benchmark datasets.
Continuous-time algorithms improve online learning performance.
problem Online learning with sequential data and minimizing overall regret.
method Extending discrete-time algorithms to continuous-time models for online linear optimization, adversarial bandit, and adversarial linear bandit.
result Optimal regret bounds are proven for continuous-time settings.
Efficiently scales continuous kernels with sparse Fourier domain learning.
problem High computational and memory demands, spectral bias in continuous kernels.
method Sparse learning in the Fourier domain.
result Efficient scaling of continuous kernels, reduced computational and memory requirements, mitigated spectral bias.
Tabular Q-Learning with learned state abstractions solves continuous control tasks.
problem Challenging reinforcement learning problems in continuous control.
method Learned state abstraction to transform continuous state-space into discrete.
result Tabular Q-Learning with learned abstractions achieves efficient learning in unseen tasks.
AGS-CL selectively updates penalties based on node importance for continual learning.
problem Catastrophic forgetting in continual learning.
method Adaptive Group Sparsity (AGS) with proximal gradient descent.
result Significantly outperforms baselines on various continual learning benchmarks.
Efficient method for learning continuous exponential families beyond Gaussian.
problem Learning continuous exponential families with unbounded support.
method Interaction Screening approach for scalable learning of continuous graphical models.
result Our estimator maintains similar accuracy and sample complexity scalings compared to alternative approaches, while improving run-time.
A new buffer system improves continual learning in RL agents by adapting to changing environments.
problem Improving RL agents' ability to learn from changing environments over time.
method Multi-timescale replay buffer combined with invariant risk minimization.
result The method shows improvement over baselines in continual learning settings.
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic forgetting. Algorithms dealing with it are gathered in the Continual Learning research…
VAR-GPs solve continual learning by updating posteriors sequentially.
problem Catastrophic forgetting in sequential learning tasks.
method Sparse inducing point approximations and auto-regressive variational distribution.
result VAR-GPs prevent catastrophic forgetting and outperform baselines.
Hybrid framework prevents forgetting in continual learning.
problem Avoiding forgetting in learning new tasks without forgetting old ones.
method Hybrid continual learning framework combining architecture growth and experience replay.
result Hybrid approach effectively avoids forgetting across multiple tasks.
A new method for continual learning in GANs learns new modes with limited data.
problem Learning new target modes with limited samples while preserving previously learned ones.
method Mode-affinity score for generative modeling, generator replay, and weighted label generation.
result Gains over state-of-the-art methods, even with fewer training samples.
Proposes Mv-TCNN for continual learning without known tasks in advance.
problem Catastrophic forgetting in continual learning.
method Multi-view Task Conditional Neural Networks (Mv-TCNN).
result Outperforms state-of-the-art continual learning models.