MemFLoRA：面向边缘 CNN 适配的低激活内存 LoRA 方法
MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge
把 LoRA 搬到边缘设备上跑 CNN，激活内存砍掉九成多，做端侧学习的人可以看看具体做法。
arXiv 论文提出 MemFLoRA，一种专为 CNN 设计的低秩适配器。作者指出 CNN 边缘适配的瓶颈不是可训练参数量，而是反向传播需保留的激活状态。该方法冻结下投影、训练尺度匹配的上投影，使保存状态降到低秩分支。在 3 个 HAR 数据集和 2 个 CNN 骨干网络上，MemFLoRA 相比全量微调减少 98.5-98.7% 的保存激活内存、94.9-97.3% 的峰值训练内存，同时达到或超过 CNN PEFT 基线。
MemFLoRA: Memory-Floor LoRA for CNN Adaptation at the Edge
On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backward pass. This paper introduces Memory-Floor LoRA (MemFLoRA), a low-rank CNN adapter built around a memory-first design principle rather than a direct application of transformer-oriented LoRA. Instead of merely reducing trainable weights, we define an activation-memory-floor criterion: trainable backward computations must not depend on full-width layer inputs. The resulting adapter freezes the down-projection, trains a scale-matched up-projection, and combines eval-mode backbone normalization with activation-minimal backward rules, reducing saved state to the low-rank branch. Evaluated on three Human Activity Recognition (HAR) datasets and two CNN backbones under subject, body-location, and sensor-placement shifts, MemFLoRA reduces saved-activation memory by 98.5-98.7% and peak training-state memory by 94.9-97.3% relative to full fine-tuning, while matching or exceeding CNN PEFT baselines.
