Online Continual Learning with Maximally Interfered Retrieval

Classés selon la proximité de leur titre et de leur résumé avec ceux de cet article. Sélectionnez-en pour les lire ensemble.

Les articles les plus proches

1. Très proche Cite cet article Pas pertinent

   Watch Your Step: Optimal Retrieval for Continual Learning at Scale

   Truman Hickok, D. Kudithipudi · 2024 · arXiv.org · preprint, non relu par les pairs · cité 2 fois · Pas encore résumé

   Résumé scientifique

   In continual learning, a model learns incrementally over time while minimizing interference between old and new tasks. One of the most widely used approaches in continual learning is referred to as replay. Replay methods support interleaved learning by storing past experiences in a replay buffer. Although there are methods for selectively constructing the buffer and reprocessing its contents, there is limited exploration of the problem of selectively retrieving samples from the buffer. Current solutions have been tested in limited settings and, more importantly, in isolation. Existing work has also not explored the impact of duplicate replays on performance. In this work, we propose a framew…

2. Très proche Cite cet article Pas pertinent

   Replay Can Provably Increase Forgetting

   Yasaman Mahdaviyeh, James Lucas, Mengye Ren et al. · 2025 · arXiv.org · preprint, non relu par les pairs · cité 6 fois · Pas encore résumé

   Résumé scientifique

   Continual learning seeks to enable machine learning systems to solve an increasing corpus of tasks sequentially. A critical challenge for continual learning is forgetting, where the performance on previously learned tasks decreases as new tasks are introduced. One of the commonly used techniques to mitigate forgetting, sample replay, has been shown empirically to reduce forgetting by retaining some examples from old tasks and including them in new training episodes. In this work, we provide a theoretical analysis of sample replay in an over-parameterized continual linear regression setting, where each task is given by a linear subspace and with enough replay samples, one would be able to eli…

3. Très proche Cite cet article Utilise cet article en profondeur Pas pertinent

   Continual Learning with Class-Level Minimally Interfered Update

   Guanglu Wang, Xianchao Zhang, Han Liu et al. · 2024 · IEEE International Conference on Acoustics, Speech, and Signal Processing · Pas encore résumé

   Résumé scientifique

   Catastrophic forgetting has become an intractable problem in the continual learning setting because previous data is not accessible when training. To mitigate this problem, memory-based continual learning methods replay previous data from a fixed-size memory buffer. Reservoir sampling, which can sample uniformly from streaming data in a single pass and randomly delete a few buffered samples to keep the memory capacity, is widely used in the memory update process. Nevertheless, the random deletion will cause the agent to miss some high-quality samples, which are more effective in overcoming forgetting. In this paper, we propose a novel memory update method, Class-level Minimally Interfered Up…

4. Très proche Pas pertinent

   An Investigation of Replay-based Approaches for Continual Learning

   Benedikt Bagus, A. Gepperth · 2021 · IEEE International Joint Conference on Neural Network · cité 51 fois · Pas encore résumé

   Résumé scientifique

   Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when real-world scenarios with multiple constraints are involved. Several solution classes have been proposed [1], of which socalled replay-based approaches seem very promising due to their simplicity and robustness. Such approaches store a subset of past samples in a dedicated memory for later processing: while this does not solve all problems, good results have been obtained. In this article, we empirically investigate replay-based approaches of continual learn…

5. Très proche Pas pertinent

   Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning

   Jason Yoo, Yunpeng Liu, Frank Wood et al. · 2024 · International Conference on Machine Learning · cité 20 fois · Pas encore résumé

   Résumé scientifique

   In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on past data. Our work demonstrates a limitation of this approach: neural networks trained with experience replay tend to have unstable optimization trajectories, impeding their overall accuracy. Surprisingly, these instabilities persist even when the replay buffer stores all previous training examples, suggesting that this issue is orthogonal to catastrophic forgetting. We minimize these instabilities through a simple modification of the optimization geometry…

6. Très proche Pas pertinent

   Information-theoretic Online Memory Selection for Continual Learning

   Sheng-Yang Sun, Daniele Calandriello, Hui-Yi Hu et al. · 2022 · International Conference on Learning Representations · cité 66 fois · Pas encore résumé

   Résumé scientifique

   A challenging problem in task-free continual learning is the online selection of a representative replay memory from data streams. In this work, we investigate the online memory selection problem from an information-theoretic perspective. To gather the most information, we propose the \textit{surprise} and the \textit{learnability} criteria to pick informative points and to avoid outliers. We present a Bayesian model to compute the criteria efficiently by exploiting rank-one matrix structures. We demonstrate that these criteria encourage selecting informative points in a greedy algorithm for online memory selection. Furthermore, by identifying the importance of \textit{the timing to update t…

7. Très proche Pas pertinent

   Continual Learning through Retrieval and Imagination

   Zhen Wang, Liu Liu, Yiqun Duan et al. · 2022 · AAAI Conference on Artificial Intelligence · cité 51 fois · Pas encore résumé

   Résumé scientifique

   Continual learning is an intellectual ability of artificial agents to learn new streaming labels from sequential data. The main impediment to continual learning is catastrophic forgetting, a severe performance degradation on previously learned tasks. Although simply replaying all previous data or continuously adding the model parameters could alleviate the issue, it is impractical in real-world applications due to the limited available resources. Inspired by the mechanism of the human brain to deepen its past impression, we propose a novel framework, Deep Retrieval and Imagination (DRI), which consists of two components: 1) an embedding network that constructs a unified embedding space witho…

8. Très proche Pas pertinent

   A rehearsal framework for computational efficiency in online continual learning

   Charalampos Davalas, Dimitrios Michail, Christos Diou et al. · 2024 · Applied intelligence (Boston) · cité 4 fois · Pas encore résumé

   Résumé scientifique

   In the realm of online continual learning, models are expected to adapt to an ever-changing environment. One of the most persistent hurdles in this adaptation is the mitigation of a phenomenon called "Catastrophic Forgetting" (CF). This critical condition occurs when models trained on non-identically distributed data lose performance in previously learned tasks. Rehearsal methods, leveraging the ability to replay older samples, aim to address this challenge by incorporating a buffer of past training samples. However, the absence of known task boundaries complicates the adaptation of current CF mitigation methods. This paper proposes a method attuned to data stream characteristics and online …

Les travaux antérieurs sur lesquels il s’appuie

1. Très proche Utilisé en profondeur par cet article Une méthode qu’il utilise Pas pertinent

   Continual Learning with Deep Generative Replay

   Hanul Shin, Jung Kwon Lee, Jaehong Kim et al. · 2017 · Artificial Intelligence · cité 2 659 fois · Résumé IA disponible

   Résumé scientifique

   Attempts to train a comprehensive artificial intelligence capable of solving multiple tasks have been impeded by a chronic problem called catastrophic forgetting. Although simply replaying all previous data alleviates the problem, it requires large memory and even worse, often infeasible in real world applications where the access to past data is limited. Inspired by the generative nature of hippocampus as a short-term memory system in primate brain, we propose the Deep Generative Replay, a novel framework with a cooperative dual model architecture consisting of a deep generative model ("generator") and a task solving model ("solver"). With only these two models, training data for previous t…

2. Très proche Utilisé en profondeur par cet article Une méthode qu’il utilise Pas pertinent

   Scalable Recollections for Continual Lifelong Learning

   M. Riemer, T. Klinger, Djallel Bouneffouf et al. · 2017 · AAAI Conference on Artificial Intelligence · cité 79 fois · Pas encore résumé

   Résumé scientifique

   Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A successful continual lifelong learning system must have three key capabilities: it must learn and adapt over time, it must not forget what it has learned, and it must be efficient in both training time and memory. Recent techniques have focused their efforts primarily on the first two capabilities while questions of efficiency remain largely unexplored. In this paper, we consider the proble…

3. Proche Utilisé en profondeur par cet article Pas pertinent

   Generative Models from the perspective of Continual Learning

   Timothée Lesort, H. Caselles-Dupré, Michael Garcia-Ortiz et al. · 2018 · IEEE International Joint Conference on Neural Network · cité 174 fois · Pas encore résumé

   Résumé scientifique

   Which generative model is the most suitable for Continual Learning? This paper aims at evaluating and comparing generative models on disjoint sequential image generation tasks. We investigate how several models learn and forget, considering various strategies: rehearsal, regularization, generative replay and fine-tuning. We used two quantitative metrics to estimate the generation quality and memory ability. We experiment with sequential tasks on three commonly used benchmarks for Continual Learning (MNIST, Fashion MNIST and CIFAR10). We found that among all models, the original GAN performs best and among Continual Learning strategies, generative replay outperforms all other methods. Even if…

4. Proche Une méthode qu’il utilise Pas pertinent

   Reinforced Continual Learning

   Ju Xu, Zhan-Xing Zhu · 2018 · Neural Information Processing Systems · cité 441 fois · Pas encore résumé

   Résumé scientifique

   Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns various tasks in a sequential fashion. In this work, a novel approach for continual learning is proposed, which searches for the best neural architecture for each coming task via sophisticatedly designed reinforcement learning strategies. We name it as Reinforced Continual Learning. Our method not only has good performance on preventing catastrophic forgetting but also fits new tasks well. The experiments on sequential classification tasks for variants of …

5. Très proche Pas pertinent

   Gradient based sample selection for online continual learning

   Rahaf Aljundi, Min Lin, Baptiste Goujaud et al. · 2019 · Neural Information Processing Systems · cité 1 119 fois · Pas encore résumé

   Résumé scientifique

   A continual learning agent learns online with a non-stationary and never-ending stream of data. The key to such learning process is to overcome the catastrophic forgetting of previously seen data, which is a well known problem of neural networks. To prevent forgetting, a replay buffer is usually employed to store the previous data for the purpose of rehearsal. Previous works often depend on task boundary and i.i.d. assumptions to properly select samples for the replay buffer. In this work, we formulate sample selection as a constraint reduction problem based on the constrained optimization view of continual learning. The goal is to select a fixed subset of constraints that best approximate t…

Les articles qui le citent

1. Très proche Utilise cet article en profondeur Pas pertinent

   Rethinking Transfer in Continual Learning: A Replay-Based Realisation

   Yang Meng, Zhenyang Liu, Zhuokai Zhao et al. · 2026 · arXiv.org · preprint, non relu par les pairs · cité 4 fois · Pas encore résumé

   Résumé scientifique

   Continual learning studies how deployed language models can continually acquire new tasks without expensive retraining from scratch. Existing methods, whether rehearsal-based (replaying stored past data) or rehearsal-free (regularising or isolating parameters), overwhelmingly target one objective: preventing catastrophic forgetting. Forward transfer, the past helping the future, has meanwhile been pursued almost exclusively through parameter reuse, with no explicit account of when transfer should be expected at all. We begin one step earlier: before designing a transfer mechanism, we ask when transfer should exist at all. We answer with a framework of three measurable conditions: the target …

2. Très proche Utilise cet article en profondeur Pas pertinent

   Balancing Plasticity and Stability via Dual-Branch Learning in Online Continual Learning

   Xu Han, Hao-Dong Lu, Hui-Yi Wang et al. · 2025 · The Web Conference · cité 3 fois · Pas encore résumé

   Résumé scientifique

   Deep learning models struggle with catastrophic forgetting in continual learning (CL), specifically online continual learning, requiring a balance between plasticity (adapting to new tasks) and stability (retaining prior knowledge). Memory replay addresses this challenge by integrating new data with stored memories, but existing methods of replaying the samples often fail to achieve an effective balance, overemphasizing either old or new knowledge. Previous works address this issue by enhancing replay buffer quality through sample selection or distilled images but overlook the model's learning process itself. To tackle this, we propose a novel dual-branch framework designed to manage the pla…

3. Très proche Utilise cet article en profondeur Pas pertinent

   CARES: Coverage-Aware Replay Exemplar Selection for Continual Learning

   Arundhati S. Shanbhag, Brian B. Moser, Federico Raue et al. · 2026 · Pas encore résumé

   Résumé scientifique

   Replay-based Continual Learning mitigates catastrophic forgetting by keeping a buffer of past samples, making buffer composition critical under a fixed memory budget. Recent coreset-based replay methods improve buffer quality using model-derived gradients, losses, or auxiliary optimization, but incur substantial computational overhead as memory is repeatedly updated. We propose CARES, a continual model-optimization-free approach for buffer construction that instead exploits the geometry of a frozen pretrained feature space using class-aware, density-weighted coverage. We evaluate CARES across balanced, imbalanced, and label-noisy streams under online class- and task-incremental settings. On …

4. Très proche Utilise cet article en profondeur Pas pertinent

   Representative-exploring Replay for Online Class-Incremental Continual Learning

   Libang Zhao, A. Tan, Si-Wei Feng et al. · 2025 · IEEE International Joint Conference on Neural Network · Pas encore résumé

   Résumé scientifique

   Online Class-Incremental Continual Learning (CICL) methods often rely on data replay, where a fixed-size memory buffer stores a small subset of previous data to mitigate catastrophic forgetting. However, as incremental tasks progress, the fixed buffer size reduces the number of exemplars stored per class, weakening their representativeness. We argue that preserving classification centers is more effective than maintaining decision boundaries with limited exemplars. This highlights the dual challenges of selecting high-quality exemplars for storage and addressing the imbalance between old and new classes. To tackle these issues, we propose the Representative Exploration Replay (RER) framework…

5. Très proche Pas pertinent

   Rehearsal revealed: The limits and merits of revisiting samples in continual learning

   Eli Verwimp, Matthias De Lange, Tinne Tuytelaars · 2021 · IEEE/CVF International Conference on Computer Vision (ICCV) · cité 80 fois · Pas encore résumé

   Résumé scientifique

   Learning from non-stationary data streams and overcoming catastrophic forgetting still poses a serious challenge for machine learning research. Rather than aiming to improve state-of-the-art, in this work we provide insight into the limits and merits of rehearsal, one of continual learning’s most established methods. We hypothesize that models trained sequentially with rehearsal tend to stay in the same low-loss region after a task has finished, but are at risk of overfitting on its sample memory, hence harming generalization. We provide both conceptual and strong empirical evidence on three benchmarks for both behaviors, bringing novel insights into the dynamics of rehearsal and continual l…