用低秩适配实现参数高效持续学习，大幅降低资源消耗。
CLoRA: Parameter-Efficient Continual Learning with Low-Rank Adaptation
- 用低秩矩阵只更新少量参数，跨任务复用同一套参数。
- 在语义分割任务上性能媲美甚至超越基线方法。
- 适合部署后计算资源受限的实时场景使用。
以往持续学习（CL）主要关注增量学习中神经网络的灾难性遗忘问题。现有方法通常在数据访问受限的条件下运行，但对计算资源无限制。然而在真实场景中，计算资源往往成为瓶颈。多数CL方法需为每个新任务重新训练整个模型，导致大模型训练开销巨大，难以在资源受限环境中应用。本文提出CLoRA，探索低秩适配（LoRA）在类别增量语义分割中的适用性。CLoRA仅使用少量可训练参数，并在整个学习过程中复用这些参数。实验表明，该方法性能与基线相当甚至更优。通过NetScore评估进一步强调，在评价CL方法时应兼顾资源效率。CLoRA显著降低训练硬件需求，适用于部署后资源受限的持续学习场景。
原文摘要 · Abstract (English)
In the past, continual learning (CL) was mostly concerned with the problem of catastrophic forgetting in neural networks, that arises when incrementally learning a sequence of tasks. Current CL methods function within the confines of limited data access, without any restrictions imposed on computational resources. However, in real-world scenarios, the latter takes precedence as deployed systems are often computationally constrained. A major drawback of most CL methods is the need to retrain the entire model for each new task. The computational demands of retraining large models can be prohibitive, limiting the applicability of CL in environments with limited resources. Through CLoRA, we explore the applicability of Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method for class-incremental semantic segmentation. CLoRA leverages a small set of parameters of the model and uses the same set for learning across all tasks. Results demonstrate the efficacy of CLoRA, achieving performance on par with and exceeding the baseline methods. We further evaluate CLoRA using NetScore, underscoring the need to factor in resource efficiency and evaluate CL methods beyond task performance. CLoRA significantly reduces the hardware requirements for training, making it well-suited for CL in resource-constrained environments after deployment.
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。