Class-Incremental Learning Using Generative Experience Replay Based on Time-aware Regularization

2023-10-05 · Zizhao Hu, Mohammad Rostami

Learning new tasks accumulatively without forgetting remains a critical challenge in continual learning. Generative experience replay addresses this challenge by synthesizing pseudo-data points for past learned tasks and later replaying them for concurrent training along with the new tasks' data. Generative replay is the best strategy for continual learning under a strict class-incremental setting when certain constraints need to be met: (i) constant model size, (ii) no pre-training dataset, and (iii) no memory buffer for storing past tasks' data. Inspired by the biological nervous system mechanisms, we introduce a time-aware regularization method to dynamically fine-tune the three training objective terms used for generative replay: supervised learning, latent regularization, and data reconstruction. Experimental results on major benchmarks indicate that our method pushes the limit of brain-inspired continual learners under such strict settings, improves memory retention, and increases the average performance over continually arriving tasks.

📄 PDF Abstract BibTeX arXiv:2310.03898

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learning Class Incremental Learning Continual Learning Incremental Learning

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Generative Negative Replay for Continual Learning

2022-04-12 · Gabriele Graffieti, Davide Maltoni, Lorenzo Pellegrini, Vincenzo Lomonaco

Learning continually is a key aspect of intelligence and a necessary ability to solve many real-life problems. One of the most effective strategies to control catastrophic forgetting, the Achilles' heel of continual lear…

Continual Learning

Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay

2021-06-17 · Yoojin Choi, Mostafa El-Khamy, Jungwon Lee

This paper proposes 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 sample…

class-incremental learning Class Incremental Learning Incremental Learning Knowledge Distillation+1

Model-Free Generative Replay for Lifelong Reinforcement Learning: Application to Starcraft-2

2022-08-09 · Zachary Daniels, Aswin Raghavan, Jesse Hostetler, Abrar Rahman 외

One approach to meet the challenges of deep lifelong reinforcement learning (LRL) is careful management of the agent's learning experiences, to learn (without forgetting) and build internal meta-models (of the tasks, env…

Lifelong learning Management reinforcement-learning Reinforcement Learning (RL)+2

Generative Replay-based Continual Zero-Shot Learning

2021-01-22 · Chandan Gautam, Sethupathy Parameswaran, Ashish Mishra, Suresh Sundaram

Zero-shot learning is a new paradigm to classify objects from classes that are not available at training time. Zero-shot learning (ZSL) methods have attracted considerable attention in recent years because of their abili…

Continual Learning Zero-Shot Learning

Generative Feature-driven Image Replay for Continual Learning

2021-06-09 · Kevin Thandiackal, Tiziano Portenier, Andrea Giovannini, Maria Gabrani 외

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and repla…

Class Incremental Learning Continual Learning Incremental Learning