用能量模型生成旧任务数据，缓解大模型学新知识时遗忘旧知识的问题。
LSEBMCL: A Latent Space Energy-Based Model for Continual Learning
- 在持续学习框架中引入能量模型作为外生生成器，动态生成历史任务数据。
- 在多个NLP任务上达到当前最优性能，有效抑制灾难性遗忘。
- 适合需要长期更新、避免知识丢失的自然语言处理应用。
持续学习在在线新闻摘要、产品分类等实际场景中日益重要。其核心挑战是灾难性遗忘——模型在学习新任务时会无意丢弃先前知识。现有方法包括存储旧类样本、微调时正则化参数，或为不同任务分配独立参数。本文提出LSEBMCL（基于潜在空间的能量模型持续学习），利用能量基模型（EBM）在训练新任务时从旧任务中采样数据点，以缓解遗忘。EBM为每个输入数据点赋予能量值，本方法将EBM层作为持续学习框架中的外生生成器，应用于NLP任务。实验表明，该方法在所有测试任务中均取得当前最优效果，验证了能量模型在NLP持续学习中的有效性。
原文摘要 · Abstract (English)
Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards previously learned knowledge when it is trained on new tasks. Existing solutions involve storing exemplars from previous classes, regularizing parameters during the fine-tuning process, or assigning different model parameters to each task. The proposed solution LSEBMCL (Latent Space Energy-Based Model for Continual Learning) in this work is to use energy-based models (EBMs) to prevent catastrophic forgetting by sampling data points from previous tasks when training on new ones. The EBM is a machine learning model that associates an energy value with each input data point. The proposed method uses an EBM layer as an outer-generator in the continual learning framework for NLP tasks. The study demonstrates the efficacy of EBM in NLP tasks, achieving state-of-the-art results in all experiments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。