GRASP: A Rehearsal Policy for Efficient Online Continual Learning

• URL: http://arxiv.org/abs/2308.13646v2
• Date: Wed, 1 May 2024 17:25:52 GMT
• Title: GRASP: A Rehearsal Policy for Efficient Online Continual Learning
• Authors: Md Yousuf Harun, Jhair Gallardo, Junyu Chen, Christopher Kanan,
• Abstract summary: Continual learning in deep neural networks (DNNs) involves incrementally accumulating knowledge from a growing data stream. A popular solution is rehearsal: storing past observations in a buffer and then sampling the buffer to update the DNN. Here, we propose a new sample selection policy called GRASP that selects the most prototypical (easy) samples first and then gradually selects less prototypical (harder) examples.
• Score: 19.277806222767964
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning (CL) in deep neural networks (DNNs) involves incrementally accumulating knowledge in a DNN from a growing data stream. A major challenge in CL is that non-stationary data streams cause catastrophic forgetting of previously learned abilities. A popular solution is rehearsal: storing past observations in a buffer and then sampling the buffer to update the DNN. Uniform sampling in a class-balanced manner is highly effective, and better sample selection policies have been elusive. Here, we propose a new sample selection policy called GRASP that selects the most prototypical (easy) samples first and then gradually selects less prototypical (harder) examples. GRASP has little additional compute or memory overhead compared to uniform selection, enabling it to scale to large datasets. Compared to 17 other rehearsal policies, GRASP achieves higher accuracy in CL experiments on ImageNet. Compared to uniform balanced sampling, GRASP achieves the same performance with 40% fewer updates. We also show that GRASP is effective for CL on five text classification datasets.

Related papers

• Subsampling Graphs with GNN Performance Guarantees [34.32848091746629]
  We introduce new subsampling methods for graph datasets. We prove that training a GNN on the subsampled data results in a bounded increase in loss compared to training on the full dataset.
  arXiv  Detail & Related papers  (2025-02-23T20:21:16Z)
• Class Balance Matters to Active Class-Incremental Learning [61.11786214164405]
  We aim to start from a pool of large-scale unlabeled data and then annotate the most informative samples for incremental learning. We propose Class-Balanced Selection (CBS) strategy to achieve both class balance and informativeness in chosen samples. Our CBS can be plugged and played into those CIL methods which are based on pretrained models with prompts tunning technique.
  arXiv  Detail & Related papers  (2024-12-09T16:37:27Z)
• Enhancing Consistency and Mitigating Bias: A Data Replay Approach for Incremental Learning [100.7407460674153]
  Deep learning systems are prone to catastrophic forgetting when learning from a sequence of tasks. To mitigate the problem, a line of methods propose to replay the data of experienced tasks when learning new tasks. However, it is not expected in practice considering the memory constraint or data privacy issue. As a replacement, data-free data replay methods are proposed by inverting samples from the classification model.
  arXiv  Detail & Related papers  (2024-01-12T12:51:12Z)
• Towards Free Data Selection with General-Purpose Models [71.92151210413374]
  A desirable data selection algorithm can efficiently choose the most informative samples to maximize the utility of limited annotation budgets. Current approaches, represented by active learning methods, typically follow a cumbersome pipeline that iterates the time-consuming model training and batch data selection repeatedly. FreeSel bypasses the heavy batch selection process, achieving a significant improvement in efficiency and being 530x faster than existing active learning methods.
  arXiv  Detail & Related papers  (2023-09-29T15:50:14Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• RPLKG: Robust Prompt Learning with Knowledge Graph [11.893917358053004]
  We propose a new method, robust prompt learning with knowledge graph (RPLKG) Based on the knowledge graph, we automatically design diverse interpretable and meaningful prompt sets. RPLKG shows a significant performance improvement compared to zero-shot learning.
  arXiv  Detail & Related papers  (2023-04-21T08:22:58Z)
• Classifier Transfer with Data Selection Strategies for Online Support Vector Machine Classification with Class Imbalance [1.2599533416395767]
  We focus on data selection strategies which limit the size of the stored training data. We show that by using the right combination of data selection criteria, it is possible to adapt the classifier and largely increase the performance.
  arXiv  Detail & Related papers  (2022-08-10T02:36:20Z)
• Active Learning at the ImageNet Scale [43.595076693347835]
  In this work, we study a combination of active learning (AL) and pretraining (SSP) on ImageNet. We find that performance on small toy datasets is not representative of performance on ImageNet due to the class imbalanced samples selected by an active learner. We propose Balanced Selection (BASE), a simple, scalable AL algorithm that outperforms random sampling consistently.
  arXiv  Detail & Related papers  (2021-11-25T02:48:51Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)
• How to distribute data across tasks for meta-learning? [59.608652082495624]
  We show that the optimal number of data points per task depends on the budget, but it converges to a unique constant value for large budgets. Our results suggest a simple and efficient procedure for data collection.
  arXiv  Detail & Related papers  (2021-03-15T15:38:47Z)
• Hop Sampling: A Simple Regularized Graph Learning for Non-Stationary Environments [12.251253742049437]
  Graph representation learning is gaining popularity in a wide range of applications, such as social networks analysis. Applying graph neural networks (GNNs) in a real-world application is still challenging due to non-stationary environments. We present Hop Sampling, a straightforward regularization method that can effectively prevent GNNs from overfishing.
  arXiv  Detail & Related papers  (2020-06-26T10:22:57Z)
• OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer [77.90012156266324]
  This paper aims to find a subspace of neural networks that can facilitate a large decision margin. We propose the Orthogonal Softmax Layer (OSL), which makes the weight vectors in the classification layer remain during both the training and test processes. Experimental results demonstrate that the proposed OSL has better performance than the methods used for comparison on four small-sample benchmark datasets.
  arXiv  Detail & Related papers  (2020-04-20T02:41:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.