Authors

* External authors

Venue

Date

Share

MocoSFL: enabling cross-client collaborative self-supervised learning

Jingtao Li

Lingjuan Lyu

Daisuke Iso

Chaitali Chakrabarti*

Michael Spranger

* External authors

ICLR 2023

2023

Abstract

Existing collaborative self-supervised learning (SSL) schemes are not suitable for cross-client applications because of their expensive computation and large local data requirements. To address these issues, we propose MocoSFL, a collaborative SSL framework based on Split Federated Learning (SFL) and Momentum Contrast (MoCo). In MocoSFL, the large backbone model is split into a small client-side model and a large server-side model, and only the small client-side model is processed locally on the client's local devices. MocoSFL has three key components: (i) vector concatenation which enables the use of small batch size and reduces computation and memory requirements by orders of magnitude; (ii) feature sharing that helps achieve high accuracy regardless of the quality and volume of local data; (iii) frequent synchronization that helps achieve better non-IID performance because of smaller local model divergence. For a 1,000-client case with non-IID data (each client only has data from 2 random classes of CIFAR-10), MocoSFL can achieve over 84% accuracy with ResNet-18 model. Next we present TAResSFL module that significantly improves the resistance to privacy threats and communication overhead with small sacrifice in accuracy for a MocoSFL system. On a Raspberry Pi 4B device, the MocoSFL-based scheme requires less than 1MB of memory and less than 40MB of communication, and consumes less than 5W power. Thus, compared to the state-of-the-art FL-based approach, MocoSFL has significant advantages in both accuracy and practicality for cross-client applications.

Related Publications

Beyond RGB: Adaptive Parallel Processing for RAW Object Detection

ICCV, 2025
Shani Gamrian, Hila Barel, Feiran Li, Masakazu Yoshimura*, Daisuke Iso

Object detection models are typically applied to standard RGB images processed through Image Signal Processing (ISP) pipelines, which are designed to enhance sensor-captured RAW images for human vision. However, these ISP functions can lead to a loss of critical information …

Image Intrinsic Scale Assessment: Bridging the Gap Between Quality and Resolution

ICCV, 2025
Vlad Hosu, Lorenzo Agnolucci, Daisuke Iso, Dietmar Saupe*

Image Quality Assessment (IQA) measures and predicts perceived image quality by human observers. Although recent studies have highlighted the critical influence that variations in the scale of an image have on its perceived quality, this relationship has not been systematica…

How to Evaluate and Mitigate IP Infringement in Visual Generative AI?

ICML, 2025
Zhenting Wang, Chen Chen, Vikash Sehwag, Minzhou Pan*, Lingjuan Lyu

The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered that the state-of-the-art visual generative models can generate content that bears a striking r…

  • HOME
  • Publications
  • MocoSFL: enabling cross-client collaborative self-supervised learning

JOIN US

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.