Looking through the past: better knowledge retention for generative replay in continual learning

• URL: http://arxiv.org/abs/2309.10012v1
• Date: Mon, 18 Sep 2023 13:45:49 GMT
• Title: Looking through the past: better knowledge retention for generative replay in continual learning
• Authors: Valeriya Khan, Sebastian Cygert, Kamil Deja, Tomasz Trzci\'nski, Bart{\l}omiej Twardowski
• Abstract summary: VAE-based generative replay is not powerful enough to generate more complex data with a greater number of classes. We propose three modifications that allow the model to learn and generate complex data. Our method outperforms other generative replay methods in various scenarios.
• Score: 18.695587430349438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In this work, we improve the generative replay in a continual learning setting to perform well on challenging scenarios. Current generative rehearsal methods are usually benchmarked on small and simple datasets as they are not powerful enough to generate more complex data with a greater number of classes. We notice that in VAE-based generative replay, this could be attributed to the fact that the generated features are far from the original ones when mapped to the latent space. Therefore, we propose three modifications that allow the model to learn and generate complex data. More specifically, we incorporate the distillation in latent space between the current and previous models to reduce feature drift. Additionally, a latent matching for the reconstruction and original data is proposed to improve generated features alignment. Further, based on the observation that the reconstructions are better for preserving knowledge, we add the cycling of generations through the previously trained model to make them closer to the original data. Our method outperforms other generative replay methods in various scenarios. Code available at https://github.com/valeriya-khan/looking-through-the-past.

Related papers

• Prioritized Generative Replay [121.83947140497655]
  We propose a prioritized, parametric version of an agent's memory, using generative models to capture online experience. This paradigm enables densification of past experience, with new generations that benefit from the generative model's generalization capacity. We show this recipe can be instantiated using conditional diffusion models and simple relevance functions.
  arXiv  Detail & Related papers  (2024-10-23T17:59:52Z)
• 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)
• Adiabatic replay for continual learning [138.7878582237908]
  generative replay spends an increasing amount of time just re-learning what is already known. We propose a replay-based CL strategy that we term adiabatic replay (AR) We verify experimentally that AR is superior to state-of-the-art deep generative replay using VAEs.
  arXiv  Detail & Related papers  (2023-03-23T10:18:06Z)
• DORE: Document Ordered Relation Extraction based on Generative Framework [56.537386636819626]
  This paper investigates the root cause of the underwhelming performance of the existing generative DocRE models. We propose to generate a symbolic and ordered sequence from the relation matrix which is deterministic and easier for model to learn. Experimental results on four datasets show that our proposed method can improve the performance of the generative DocRE models.
  arXiv  Detail & Related papers  (2022-10-28T11:18:10Z)
• Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue [80.05509768165135]
  generative replay methods are widely employed to consolidate past knowledge with generated pseudo samples. Most existing generative replay methods use only a single task-specific token to control their models. We propose a novel method, prompt conditioned VAE for lifelong learning, to enhance generative replay by incorporating tasks' statistics.
  arXiv  Detail & Related papers  (2022-10-14T13:12:14Z)
• Bypassing Logits Bias in Online Class-Incremental Learning with a Generative Framework [15.345043222622158]
  We focus on online class-incremental learning setting in which new classes emerge over time. Almost all existing methods are replay-based with a softmax classifier. We propose a novel generative framework based on the feature space.
  arXiv  Detail & Related papers  (2022-05-19T06:54:20Z)
• Generative Negative Replay for Continual Learning [13.492896179777835]
  Achilles' heel of continual learning is storing part of the old data and replaying them interleaved with new experiences. Generative replay is using generative models to provide replay patterns on demand. We show that, while the generated data are usually not able to improve the classification accuracy for the old classes, they can be effective as negative examples to better learn the new classes.
  arXiv  Detail & Related papers  (2022-04-12T14:38:00Z)
• Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay [49.691610143011566]
  We propose two novel knowledge transfer techniques for class-incremental learning (CIL) First, we propose data-free generative replay (DF-GR) to mitigate catastrophic forgetting in CIL by using synthetic samples from a generative model. Second, we introduce dual-teacher information distillation (DT-ID) for knowledge distillation from two teachers to one student.
  arXiv  Detail & Related papers  (2021-06-17T22:13:15Z)
• Generative Feature Replay with Orthogonal Weight Modification for Continual Learning [20.8966035274874]
  generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting. We propose to replay penultimate layer feature with a generative model; 2) leverage a self-supervised auxiliary task to further enhance the stability of feature. Empirical results on several datasets show our method always achieves substantial improvement over powerful OWM.
  arXiv  Detail & Related papers  (2020-05-07T13:56:22Z)
• Generative Feature Replay For Class-Incremental Learning [46.88667212214957]
  We consider a class-incremental setting which means that the task-ID is unknown at inference time. The imbalance between old and new classes typically results in a bias of the network towards the newest ones. We propose a solution based on generative feature replay which does not require any exemplars.
  arXiv  Detail & Related papers  (2020-04-20T10:58:20Z)

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.