A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal

• URL: http://arxiv.org/abs/2209.13917v1
• Date: Wed, 28 Sep 2022 08:43:35 GMT
• Title: A simple but strong baseline for online continual learning: Repeated Augmented Rehearsal
• Authors: Yaqian Zhang, Bernhard Pfahringer, Eibe Frank, Albert Bifet, Nick Jin Sean Lim, Yunzhe Jia
• Abstract summary: Online continual learning (OCL) aims to train neural networks incrementally from a non-stationary data stream with a single pass through data. Rehearsal-based methods attempt to approximate the observed input distributions over time with a small memory and revisit them later to avoid forgetting. We provide theoretical insights on the inherent memory overfitting risk from the viewpoint of biased and dynamic empirical risk minimization.
• Score: 13.075018350152074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Online continual learning (OCL) aims to train neural networks incrementally from a non-stationary data stream with a single pass through data. Rehearsal-based methods attempt to approximate the observed input distributions over time with a small memory and revisit them later to avoid forgetting. Despite its strong empirical performance, rehearsal methods still suffer from a poor approximation of the loss landscape of past data with memory samples. This paper revisits the rehearsal dynamics in online settings. We provide theoretical insights on the inherent memory overfitting risk from the viewpoint of biased and dynamic empirical risk minimization, and examine the merits and limits of repeated rehearsal. Inspired by our analysis, a simple and intuitive baseline, Repeated Augmented Rehearsal (RAR), is designed to address the underfitting-overfitting dilemma of online rehearsal. Surprisingly, across four rather different OCL benchmarks, this simple baseline outperforms vanilla rehearsal by 9%-17% and also significantly improves state-of-the-art rehearsal-based methods MIR, ASER, and SCR. We also demonstrate that RAR successfully achieves an accurate approximation of the loss landscape of past data and high-loss ridge aversion in its learning trajectory. Extensive ablation studies are conducted to study the interplay between repeated and augmented rehearsal and reinforcement learning (RL) is applied to dynamically adjust the hyperparameters of RAR to balance the stability-plasticity trade-off online.

Related papers

• Heterogeneous Learning Rate Scheduling for Neural Architecture Search on Long-Tailed Datasets [0.0]
  We propose a novel adaptive learning rate scheduling strategy tailored for the architecture parameters of DARTS. Our approach dynamically adjusts the learning rate of the architecture parameters based on the training epoch, preventing the disruption of well-trained representations.
  arXiv  Detail & Related papers  (2024-06-11T07:32:25Z)
• Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation [14.25441464051506]
  We propose Contrastive Continual Learning via Importance Sampling (CCLIS) to preserve knowledge by recovering previous data distributions. We also present the Prototype-instance Relation Distillation (PRD) loss, a technique designed to maintain the relationship between prototypes and sample representations.
  arXiv  Detail & Related papers  (2024-03-07T15:47:52Z)
• Take the Bull by the Horns: Hard Sample-Reweighted Continual Training Improves LLM Generalization [165.98557106089777]
  A key challenge is to enhance the capabilities of large language models (LLMs) amid a looming shortage of high-quality training data. Our study starts from an empirical strategy for the light continual training of LLMs using their original pre-training data sets. We then formalize this strategy into a principled framework of Instance-Reweighted Distributionally Robust Optimization.
  arXiv  Detail & Related papers  (2024-02-22T04:10:57Z)
• Noisy Self-Training with Synthetic Queries for Dense Retrieval [49.49928764695172]
  We introduce a novel noisy self-training framework combined with synthetic queries. Experimental results show that our method improves consistently over existing methods. Our method is data efficient and outperforms competitive baselines.
  arXiv  Detail & Related papers  (2023-11-27T06:19:50Z)
• Prioritized Trajectory Replay: A Replay Memory for Data-driven Reinforcement Learning [52.49786369812919]
  We propose a memory technique, (Prioritized) Trajectory Replay (TR/PTR), which extends the sampling perspective to trajectories. TR enhances learning efficiency by backward sampling of trajectories that optimize the use of subsequent state information. We demonstrate the benefits of integrating TR and PTR with existing offline RL algorithms on D4RL.
  arXiv  Detail & Related papers  (2023-06-27T14:29:44Z)
• PCR: Proxy-based Contrastive Replay for Online Class-Incremental Continual Learning [16.67238259139417]
  Existing replay-based methods effectively alleviate this issue by saving and replaying part of old data in a proxy-based or contrastive-based replay manner. We propose a novel replay-based method called proxy-based contrastive replay (PCR)
  arXiv  Detail & Related papers  (2023-04-10T06:35:19Z)
• Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation [7.6146285961466]
  We consider the recently developed and theoretically rigorous reverse experience replay (RER) We show via experiments that this has a better performance than techniques like prioritized experience replay (PER) on various tasks.
  arXiv  Detail & Related papers  (2022-06-07T10:42:02Z)
• Stratified Experience Replay: Correcting Multiplicity Bias in Off-Policy Reinforcement Learning [17.3794999533024]
  We show that deep RL appears to struggle in the presence of extraneous data. Recent works have shown that the performance of Deep Q-Network (DQN) degrades when its replay memory becomes too large. We re-examine the motivation for sampling uniformly over a replay memory, and find that it may be flawed when using function approximation.
  arXiv  Detail & Related papers  (2021-02-22T19:29:18Z)
• Critic Regularized Regression [70.8487887738354]
  We propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR) We find that CRR performs surprisingly well and scales to tasks with high-dimensional state and action spaces.
  arXiv  Detail & Related papers  (2020-06-26T17:50:26Z)
• Provably Efficient Causal Reinforcement Learning with Confounded Observational Data [135.64775986546505]
  We study how to incorporate the dataset (observational data) collected offline, which is often abundantly available in practice, to improve the sample efficiency in the online setting. We propose the deconfounded optimistic value iteration (DOVI) algorithm, which incorporates the confounded observational data in a provably efficient manner.
  arXiv  Detail & Related papers  (2020-06-22T14:49:33Z)
• Continual Learning in Recurrent Neural Networks [67.05499844830231]
  We evaluate the effectiveness of continual learning methods for processing sequential data with recurrent neural networks (RNNs) We shed light on the particularities that arise when applying weight-importance methods, such as elastic weight consolidation, to RNNs. We show that the performance of weight-importance methods is not directly affected by the length of the processed sequences, but rather by high working memory requirements.
  arXiv  Detail & Related papers  (2020-06-22T10:05:12Z)

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.