Study examines how training regime affects neural networks' forgetting.
problem Catastrophic forgetting in neural networks when learning multiple tasks sequentially.
method Analyzes the impact of different training regimes (learning rate, batch size, regularization) on forgetting.
result Training regimes that widen tasks' local minima help prevent catastrophic forgetting.
Improved rates for continual learning using SGD and last-iterate analysis.
problem Forgetting in overparameterized models after fitting multiple tasks.
method Developed novel SGD upper bounds for continual linear models and analyzed their performance.
result Established universal forgetting rates for continual learning.
Paper proposes machine unlearning method to forget user data from neural networks.
problem Memorization of user data in neural networks violates GDPR's right to be forgotten.
method Proposes Forsaken method to measure and achieve high forgetting rates without significant accuracy loss.
result Forsaken method achieves over 90% forgetting rate with less than 5% accuracy loss.
Deep networks retain initial bias after training, affecting generalization.
problem Understanding how much initial bias in neural networks survives training.
method Introduced initialization memory to measure initial bias's survival.
result SGD can preserve initial bias, while Adam-family methods erase it.
Study shows how task similarity affects forgetting in teacher-student setup.
problem Catastrophic forgetting in continual learning.
method Extended teacher-student setup to multiple teachers, analyzing similarity between tasks.
result Task similarity, whether at readouts or features, influences forgetting and transfer.
Study on neural networks forgetting in continual learning.
problem Forgetting in neural networks during continual learning.
method Gradient descent analysis on XOR-cluster datasets.
result Explicit bounds on forgetting rate and generalization gap.
Paper proposes a method to maintain ASR performance on new tasks without forgetting old ones.
problem Mitigating forgetting in ASR models when learning new tasks.
method A novel explainability-based knowledge distillation combined with response-based knowledge distillation.
result Our method outperforms existing ones in mitigating forgetting on multi-stage sequential training tasks.
In recent years, deep neural networks have found success in replicating human-level cognitive skills, yet they suffer from several major obstacles. One significant limitation is the inability to learn new tasks without forgetting previously learned tasks, a shortcoming known as catastrophic forgetting. In this research…
Solves large-scale metric constrained problems using Project and Forget algorithm.
problem Finding consistent metric representations for large dissimilarity datasets.
method Active set algorithm with Bregman projections, converges to global optimal solution.
result Algorithm efficiently solves metric constrained problems with exponentially many constraints.
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.
Adaptive online learning algorithm improves history forgetting in nonstationary environments.
problem Adversarial nonstationary environments where future data can be very different from past data.
method Discounted regret in online convex optimization, FTRL-based algorithm, adaptive learning rate.
result Improves classical gradient descent with constant learning rate in online convex optimization.
We study the relationship between catastrophic forgetting and properties of task sequences. In particular, given a sequence of tasks, we would like to understand which properties of this sequence influence the error rates of continual learning algorithms trained on the sequence. To this end, we propose a new procedure …
Continual learning models allow to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios in which the models are trained using different data with various distributions, neural networks tend to forget the previously learned knowledge. This phenomenon is often referr…
FAST improves fast and stable task adaptation in DNNs.
problem Catastrophic forgetting in fine-tuned pretrained models.
method Introducing FAST, an easy-to-implement fine-tuning algorithm.
result FAST learns target tasks faster and retains source knowledge longer.
Catastrophic forgetting occurs when a neural network loses the information learned in a previous task after training on subsequent tasks. This problem remains a hurdle for artificial intelligence systems with sequential learning capabilities. In this paper, we propose a task-based hard attention mechanism that preserve…
As more and more people shift their movie watching online, competition between movie viewing websites are getting more and more intense. Therefore, it has become incredibly important to accurately predict a given user's watching list to maximize the chances of keeping the user on the platform. Recent studies have sugge…
Adam optimizer leads to more forgetting in neural networks.
problem Understanding and quantifying catastrophic forgetting in neural networks.
method Comparative analysis of various optimization algorithms and metrics in different learning scenarios.
result Adam optimizer causes more forgetting compared to classical algorithms like SGD.
This paper investigates how forgetting affects neural network representations and stabilizes deeper layers.
problem Catastrophic forgetting in machine learning models trained on sequential tasks.
method Representational analysis techniques and empirical studies on CIFAR-10 and CIFAR-100 datasets.
result Deeper layers are disproportionately the source of forgetting, and methods to mitigate forgetting stabilize these layers.
New theory explains forgetting in learning algorithms.
problem Tendency of learning algorithms to forget past knowledge.
method Proposes a self-consistency theory of forgetting as a loss of predictive information.
result Exact Bayesian inference allows for adaptation without forgetting.
The paper proposes selective forgetting for deep neural networks at a finer level than samples.
problem Selective forgetting of deep neural networks to handle outliers, poisoned data, or sensitive information.
method Formulated selective forgetting at a finer level than samples, introduced as an optimization problem on three criteria.
result Experimental results show the model can forget specific information for classification, improving accuracy in specific cases.
The paper analyzes how forgetting in LLMs is linked to simple task-upstream example associations.
problem Forgetting of upstream knowledge in fine-tuned LLMs.
method Empirical analysis of forgotten examples in N upstream examples after M new tasks, using low-rank matrix approximation. result Forgetting can be predicted efficiently using matrix completion over empirical associations.
LoRA fine-tuning causes forgetting, studied via particle system dynamics.
problem Catastrophic forgetting in LoRA fine-tuning.
method Mean-field self-attention model, partial differential equations, dynamical systems.
result Characterization of phase transitions in forgetting behavior.
Bayesian online meta-learning framework tackles catastrophic forgetting in few-shot classification.
problem Catastrophic forgetting in few-shot classification problems.
method Bayesian online learning, meta-learning, Laplace approximation, variational inference.
result Framework effectively achieves goal of overcoming catastrophic forgetting in few-shot classification.
Study analyzes catastrophic forgetting in continual learning using teacher-student networks.
problem Catastrophic forgetting in continuously learning systems.
method Teacher-student learning framework, similarity of input distributions and target functions.
result Network can avoid catastrophic forgetting with small input distribution similarity and large target function similarity.
Paper tackles catastrophic forgetting in sequential learning.
problem Catastrophic forgetting in sequential learning.
method Regularizes training with sketches of Jacobian matrix of past data.
result Proves overcoming catastrophic forgetting for linear and wide neural networks.
This work tackles catastrophic forgetting in neural networks by mimicking brain's metaplasticity.
problem Catastrophic forgetting in neural networks, where new tasks erase previously learned ones.
method Interpreting binarized neural networks as metaplastic systems, adjusting their training technique.
result Training technique reduces catastrophic forgetting without needing previously presented data.
Overparameterization helps prevent forgetting in sequential learning tasks.
problem Catastrophic forgetting in continual learning systems.
method Analytical study of gradient descent with linear regression model.
result Overparameterization can mitigate forgetting in a two-task setting.
Interpreting the behaviors of Deep Neural Networks (usually considered as a black box) is critical especially when they are now being widely adopted over diverse aspects of human life. Taking the advancements from Explainable Artificial Intelligent, this paper proposes a novel technique called Auto DeepVis to dissect c…
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.
Given data with noisy labels, over-parameterized deep networks can gradually memorize the data, and fit everything in the end. Although equipped with corrections for noisy labels, many learning methods in this area still suffer overfitting due to undesired memorization. In this paper, to relieve this issue, we propose …
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.
Adaptive model learns from time series data with changing distributions.
problem Predicting time series data under distribution shift.
method Formulates distribution shift as weighted empirical risk minimization. Uses a gradient-based learning method for a forgetting mechanism.
result Proposes an efficient method for adaptive time series prediction.
Model collapse occurs quickly for synthetic data generated by previous models.
problem Model quality degrades over recursive training on synthetic data.
method Theoretical and experimental evaluations of discrete and Gaussian distributions under near ML estimation.
result Model collapse for discrete distributions is approximately linearly dependent on the number of times a word occurs in the original corpus, and for Gaussian models, the standard deviation reduces to zero roughly at n iterations.
In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in which the sequence of changing model distributions is the sequence of tasks to the d…
Synthetic data helps prevent forgetting when learning sequentially.
problem Catastrophic forgetting in neural networks.
method Generate synthetic data via two-step optimisation process using meta-gradients.
result Training on synthetic data prevents forgetting when learning sequentially.
A new method prevents forgetting during knowledge transfer.
problem Catastrophic forgetting in transfer learning.
method Transfer without Forgetting (TwF) using a fixed pretrained network.
result TwF outperforms other CL methods by 4.81% in Class-Incremental accuracy.
Holomorphic maps between moduli spaces are shown to be forgetful for large g.
problem Characterizing holomorphic maps between moduli spaces.
method Proving that only forgetful maps are non-constant for large g.
result Forgetful maps are the only non-constant holomorphic maps between moduli spaces for g≥4. Proposes a new method to prevent forgetting in neural networks.
problem Catastrophic forgetting in neural networks.
method Total absolute signal passing through each connection.
result Simpler and closer to brain processes.
Dynamic memory prevents forgetting in continuous learning of medical images.
problem Catastrophic forgetting in machine learning models over time due to domain shifts.
method Dynamic memory to store and replay diverse training data subsets.
result Dynamic memory mitigates forgetting without knowing when shifts occur.
Paper proposes a new pipeline for few-shot classification using forget-update module and channel vector sequence.
problem Few-shot classification with limited support samples.
method Channel vector sequence construction module and forget-update module.
result Pipeline achieves state-of-the-art results on various datasets.
Survival rates for colorectal cancer are higher when polyps are detected at an early stage and can be removed before they develop into malignant tumors. Automated polyp detection, which is dominated by deep learning based methods, seeks to improve early detection of polyps. However, current efforts rely heavily on the …
We consider the sequential Bayesian optimization problem with bandit feedback, adopting a formulation that allows for the reward function to vary with time. We model the reward function using a Gaussian process whose evolution obeys a simple Markov model. We introduce two natural extensions of the classical Gaussian pr…
Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks. While this phenomenon was studied in the past, there is only very limited recent research on this phenomenon. We propose a method for determining the contribution of individual parameters in an ANN to catastrophic…
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.
Dropout helps a stable network learn new tasks without forgetting old ones.
problem Catastrophic forgetting in neural networks when learning multiple tasks.
method Investigate the relationship between dropout and stability in neural networks, showing dropout acts as an implicit gating mechanism.
result Dropout stabilizes a network's learning, allowing it to learn new tasks without forgetting old ones.
Study on reducing forgetting in neural networks using compression theory.
problem Catastrophic forgetting in neural networks.
method Defined forgetting as increased description lengths, compared variational posterior approaches to prequential coding methods.
result Proposed a new continual learning method combining ML plug-in and Bayesian mixture codes.
We study forgetful maps between Deligne-Mostow moduli spaces of weighted points on P^1, and classify the forgetful maps that extend to a map of orbifolds between the stable completions. The cases where this happens include the Livné fibrations and the Mostow/Toledo maps between complex hyperbolic surfaces. They also in…
We quantify forgetting in post-training models, distinguishing mass and drift.
problem Understanding and preventing forgetting in post-training generative models.
method Developed theoretical results under a two-mode mixture abstraction, formalizing mass and drift forgetting.
result Forgetting can be precisely quantified based on divergence direction, geometric overlap, and training regime.