FedMef: Towards Memory-efficient Federated Dynamic Pruning

Hong Huang

Weiming Zhuang

Chen Chen

Lingjuan Lyu

CVPR 2024



Federated learning (FL) promotes decentralized training while prioritizing data confidentiality. However, its application on resource-constrained devices is challenging due to the high demand for computation and memory resources for training deep learning models. Neural network pruning techniques, such as dynamic pruning, could enhance model efficiency, but directly adopting them in FL still poses substantial challenges, including post-pruning performance degradation, high activation memory, etc. To address these challenges, we propose FedMef, a novel and memory-efficient federated dynamic pruning framework. FedMef comprises two key components. First, we introduce the budget-aware extrusion that maintains pruning efficiency while preserving post-pruning performance by salvaging crucial information from parameters marked for pruning within a given budget. Second, we propose scaled activation pruning to effectively reduce activation memory, which is particularly beneficial for deploying FL to memory-limited devices. Extensive experiments demonstrate the effectiveness of our proposed FedMef. In particular, it achieves a significant reduction of 28.5% in memory footprint compared to state-of-the-art methods while obtaining superior accuracy.

Related Publications

PerceptAnon: Exploring the Human Perception of Image Anonymization Beyond Pseudonymization for GDPR

ICML, 2024
Kartik Patwari, Chen-Nee Chuah*, Lingjuan Lyu, Vivek Sharma

Current image anonymization techniques, largely focus on localized pseudonymization, typically modify identifiable features like faces or full bodies and evaluate anonymity through metrics such as detection and re-identification rates. However, this approach often overlooks …

COALA: A Practical and Vision-Centric Federated Learning Platform

ICML, 2024
Weiming Zhuang, Jian Xu, Chen Chen, Jingtao Li, Lingjuan Lyu

We present COALA, a vision-centric Federated Learning (FL) platform, and a suite of benchmarks for practical FL scenarios, which we categorize as task, data, and model levels. At the task level, COALA extends support from simple classification to 15 computer vision tasks, in…

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

ICML, 2024
Zhenting Wang, Vikash Sehwag, Chen Chen, Lingjuan Lyu, Dimitris N. Metaxas*, Shiqing Ma*

Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models. It is, therefore, necessary to analyze the origin of images by inferring if a particular imag…


Shape the Future of AI with Sony AI

We want to hear from those of you who have a strong desire
to shape the future of AI.