paper-with-me

Papers

LANCE: Low Rank Activation Compression for Efficient On-Device Continual Learning

2025-09-25 · Marco Paul E. Apolinario, Kaushik Roy arxiv

On-device learning is essential for personalization, privacy, and long-term adaptation in resource-constrained environments. Achieving this requires efficient learning, both fine-tuning existing models and continually acquiring new tasks without catastrophic forgetting. Yet both settings are constrained by high memory cost of storing activations during backpropagation. Existing activation compression methods reduce this cost but rely on repeated low-rank decompositions, introducing computational overhead. Also, such methods have not been explored for continual learning. We propose LANCE (Low-rank Activation Compression), a framework that performs one-shot higher-order Singular Value Decomposition (SVD) to obtain a reusable low-rank subspace for activation projection. This eliminates repeated decompositions, reducing both memory and computation. Moreover, fixed low-rank subspaces further enable on-device continual learning by allocating tasks to orthogonal subspaces without storing large task-specific matrices. Experiments show that LANCE reduces activation storage up to 250$\times$ while maintaining accuracy comparable to full backpropagation on CIFAR-10/100, Oxford-IIIT Pets, Flowers102, and CUB-200 datasets. On continual learning benchmarks (Split CIFAR-100, Split MiniImageNet, 5-Datasets), it performs competitively with orthogonal gradient projection methods at a fraction of the memory cost. These results position LANCE as a practical and scalable solution for efficient fine-tuning and continual learning on edge devices.

📄 PDF Abstract BibTeX arXiv:2509.21617

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

SplitLite: Low-Rank Residual Compression for Split Learning

2026-08-24 · Tao Li, Yulin Tang, Qi Guo, Xianhao Chen arxiv

Federated fine-tuning of on-device large language models (LLMs) faces a significant computing burden. To overcome this limitation, split learning (SL) has emerged as a promising solution, which offloads the primary train…

FlashSVD: Memory-Efficient Inference with Streaming for Low-Rank Models

2025-08-02 · Zishan Shao, Yixiao Wang, Qinsi Wang, Ting Jiang 외 arxiv

Singular Value Decomposition (SVD) has recently seen a surge of interest as a simple yet powerful tool for large language models (LLMs) compression, with a growing number of works demonstrating 20-80% parameter reduction…

Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM

2025-10-07 · Ryan Solgi, Parsa Madinei, Jiayi Tian, Rupak Swaminathan 외 arxiv

Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment. We present a novel low-rank compression …

Model Compression

BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression

2025-09-29 · David González-Martínez arxiv

Activation-aware low-rank factorization techniques yield strong compression results but are generally confined to linear layers, while existing whitening-based theory typically makes an implicit full-rank assumption on a…

Model Compression

Memory-Efficient Vision Transformers: An Activation-Aware Mixed-Rank Compression Strategy

2024-02-08 · Seyedarmin Azizi, Mahdi Nazemi, Massoud Pedram

As Vision Transformers (ViTs) increasingly set new benchmarks in computer vision, their practical deployment on inference engines is often hindered by their significant memory bandwidth and (on-chip) memory footprint req…

Model Compression