Poster
in
Workshop: ICML 2024 Workshop on Foundation Models in the Wild
Federated Fine-Tuning of Vision Foundation Models via Probabilistic Masking
Vasileios Tsouvalas · Yuki Asano · Aaqib Saeed
Keywords: [ Fine-Tuning ] [ probabilistic masking ] [ probabilistic filters ] [ foundation models ] [ federated learning ]
Abstract:
Foundation Models (FMs) have revolutionized machine learning with their adaptability and high performance across tasks; yet, their integration into Federated Learning (FL) is challenging due to substantial communication overhead from their extensive parameterization. We present DeltaMask, a novel method that efficiently fine-tunes FMs in FL at an ultra-low bitrate, well below 1 bpp. DeltaMask employs stochastic masking to detect highly effective subnetworks within FMs and leverage stochasticity and sparsity in client masks to compress updates into a compact grayscale image using probabilistic filters, deviating from traditional weight training approaches. Our comprehensive evaluations across various datasets and architectures demonstrate DeltaMask efficiently achieves bitrates as low as 0.09 bpp, enhancing communication efficiency while maintaining FMs performance, as measured on 8 datasets and 5 pre-trained models of various network architectures.
Chat is not available.