Densely Distilling Cumulative Knowledge for Continual Learning

• URL: http://arxiv.org/abs/2405.09820v1
• Date: Thu, 16 May 2024 05:37:06 GMT
• Title: Densely Distilling Cumulative Knowledge for Continual Learning
• Authors: Zenglin Shi, Pei Liu, Tong Su, Yunpeng Wu, Kuien Liu, Yu Song, Meng Wang,
• Abstract summary: Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. We propose Dense Knowledge Distillation (DKD) to distill the cumulative knowledge of all the previous tasks. Our DKD outperforms recent state-of-the-art baselines across diverse benchmarks and scenarios.
• Score: 14.343655566551213
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Continual learning, involving sequential training on diverse tasks, often faces catastrophic forgetting. While knowledge distillation-based approaches exhibit notable success in preventing forgetting, we pinpoint a limitation in their ability to distill the cumulative knowledge of all the previous tasks. To remedy this, we propose Dense Knowledge Distillation (DKD). DKD uses a task pool to track the model's capabilities. It partitions the output logits of the model into dense groups, each corresponding to a task in the task pool. It then distills all tasks' knowledge using all groups. However, using all the groups can be computationally expensive, we also suggest random group selection in each optimization step. Moreover, we propose an adaptive weighting scheme, which balances the learning of new classes and the retention of old classes, based on the count and similarity of the classes. Our DKD outperforms recent state-of-the-art baselines across diverse benchmarks and scenarios. Empirical analysis underscores DKD's ability to enhance model stability, promote flatter minima for improved generalization, and remains robust across various memory budgets and task orders. Moreover, it seamlessly integrates with other CL methods to boost performance and proves versatile in offline scenarios like model compression.

Related papers

• Active Data Curation Effectively Distills Large-Scale Multimodal Models [66.23057263509027]
  Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. In this work we explore an alternative, yet simple approach -- active data curation as effective distillation for contrastive multimodal pretraining. Our simple online batch selection method, ACID, outperforms strong KD baselines across various model-, data- and compute-configurations.
  arXiv  Detail & Related papers  (2024-11-27T18:50:15Z)
• ICL-TSVD: Bridging Theory and Practice in Continual Learning with Pre-trained Models [103.45785408116146]
  Continual learning (CL) aims to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging large pre-trained models that generalize well to downstream tasks. However, such methods lack theoretical guarantees, making them prone to unexpected failures. We bridge this gap by integrating an empirically strong approach into a principled framework, designed to prevent forgetting.
  arXiv  Detail & Related papers  (2024-10-01T12:58:37Z)
• Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation [33.21314371624318]
  Knowledge distillation (KD) is a promising solution, enabling the transfer of capabilities from larger teacher LLMs to more compact student models. We introduce the Multi-Stage Balanced Distillation (BalDistill) framework, which iteratively balances training data within a fixed computational budget. BalDistill achieves state-of-the-art performance across diverse long-tailed datasets, enhancing both the efficiency and efficacy of the distilled models.
  arXiv  Detail & Related papers  (2024-06-19T00:01:14Z)
• Dynamic Sub-graph Distillation for Robust Semi-supervised Continual Learning [47.64252639582435]
  We focus on semi-supervised continual learning (SSCL), where the model progressively learns from partially labeled data with unknown categories. We propose a novel approach called Dynamic Sub-Graph Distillation (DSGD) for semi-supervised continual learning.
  arXiv  Detail & Related papers  (2023-12-27T04:40:12Z)
• NEVIS'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research [96.53307645791179]
  We introduce the Never-Ending VIsual-classification Stream (NEVIS'22), a benchmark consisting of a stream of over 100 visual classification tasks. Despite being limited to classification, the resulting stream has a rich diversity of tasks from OCR, to texture analysis, scene recognition, and so forth. Overall, NEVIS'22 poses an unprecedented challenge for current sequential learning approaches due to the scale and diversity of tasks.
  arXiv  Detail & Related papers  (2022-11-15T18:57:46Z)
• Self-Distillation from the Last Mini-Batch for Consistency Regularization [14.388479145440636]
  We propose an efficient and reliable self-distillation framework, named Self-Distillation from Last Mini-Batch (DLB) Our proposed mechanism guides the training stability and consistency, resulting in robustness to label noise. Experimental results on three classification benchmarks illustrate that our approach can consistently outperform state-of-the-art self-distillation approaches.
  arXiv  Detail & Related papers  (2022-03-30T09:50:24Z)
• vCLIMB: A Novel Video Class Incremental Learning Benchmark [53.90485760679411]
  We introduce vCLIMB, a novel video continual learning benchmark. vCLIMB is a standardized test-bed to analyze catastrophic forgetting of deep models in video continual learning. We propose a temporal consistency regularization that can be applied on top of memory-based continual learning methods.
  arXiv  Detail & Related papers  (2022-01-23T22:14:17Z)
• Task-agnostic Continual Learning with Hybrid Probabilistic Models [75.01205414507243]
  We propose HCL, a Hybrid generative-discriminative approach to Continual Learning for classification. The flow is used to learn the data distribution, perform classification, identify task changes, and avoid forgetting. We demonstrate the strong performance of HCL on a range of continual learning benchmarks such as split-MNIST, split-CIFAR, and SVHN-MNIST.
  arXiv  Detail & Related papers  (2021-06-24T05:19:26Z)
• Continual Learning From Unlabeled Data Via Deep Clustering [7.704949298975352]
  Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. We introduce a new framework to make continual learning feasible in unsupervised mode by using pseudo label obtained from cluster assignments to update model.
  arXiv  Detail & Related papers  (2021-04-14T23:46:17Z)
• Continual Learning with Node-Importance based Adaptive Group Sparse Regularization [30.23319528662881]
  We propose a novel regularization-based continual learning method, dubbed as Adaptive Group Sparsity based Continual Learning (AGS-CL) Our method selectively employs the two penalties when learning each node based its the importance, which is adaptively updated after learning each new task.
  arXiv  Detail & Related papers  (2020-03-30T18:21:04Z)

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.