FedMBridge: Bridgeable Multimodal Federated Learning

Jiayi Chen, Aidong Zhang
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:7667-7686, 2024.

Abstract

Multimodal Federated Learning (MFL) addresses the setup of multiple clients with diversified modality types (e.g. image, text, video, and audio) working together to improve their local personal models in a data-privacy manner. Prior MFL works rely on restrictive compositional neural architecture designs to ensure inter-client information sharing via blockwise model aggregation, limiting their applicability in the real-world Architecture-personalized MFL (AMFL) scenarios, where clients may have distinguished multimodal interaction strategies and there is no restriction on local architecture design. The key challenge in AMFL is how to automatically and efficiently tackle the two heterogeneity patterns–statistical and architecture heterogeneity–while maximizing the beneficial information sharing among clients. To solve this challenge, we propose FedMBridge, which leverages a topology-aware hypernetwork to act as a bridge that can automatically balance and digest the two heterogeneity patterns in a communication-efficient manner. Our experiments on four AMFL simulations demonstrate the efficiency and effectiveness of our proposed approach.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-chen24ba, title = {{F}ed{MB}ridge: Bridgeable Multimodal Federated Learning}, author = {Chen, Jiayi and Zhang, Aidong}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {7667--7686}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/chen24ba/chen24ba.pdf}, url = {https://proceedings.mlr.press/v235/chen24ba.html}, abstract = {Multimodal Federated Learning (MFL) addresses the setup of multiple clients with diversified modality types (e.g. image, text, video, and audio) working together to improve their local personal models in a data-privacy manner. Prior MFL works rely on restrictive compositional neural architecture designs to ensure inter-client information sharing via blockwise model aggregation, limiting their applicability in the real-world Architecture-personalized MFL (AMFL) scenarios, where clients may have distinguished multimodal interaction strategies and there is no restriction on local architecture design. The key challenge in AMFL is how to automatically and efficiently tackle the two heterogeneity patterns–statistical and architecture heterogeneity–while maximizing the beneficial information sharing among clients. To solve this challenge, we propose FedMBridge, which leverages a topology-aware hypernetwork to act as a bridge that can automatically balance and digest the two heterogeneity patterns in a communication-efficient manner. Our experiments on four AMFL simulations demonstrate the efficiency and effectiveness of our proposed approach.} }
Endnote
%0 Conference Paper %T FedMBridge: Bridgeable Multimodal Federated Learning %A Jiayi Chen %A Aidong Zhang %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-chen24ba %I PMLR %P 7667--7686 %U https://proceedings.mlr.press/v235/chen24ba.html %V 235 %X Multimodal Federated Learning (MFL) addresses the setup of multiple clients with diversified modality types (e.g. image, text, video, and audio) working together to improve their local personal models in a data-privacy manner. Prior MFL works rely on restrictive compositional neural architecture designs to ensure inter-client information sharing via blockwise model aggregation, limiting their applicability in the real-world Architecture-personalized MFL (AMFL) scenarios, where clients may have distinguished multimodal interaction strategies and there is no restriction on local architecture design. The key challenge in AMFL is how to automatically and efficiently tackle the two heterogeneity patterns–statistical and architecture heterogeneity–while maximizing the beneficial information sharing among clients. To solve this challenge, we propose FedMBridge, which leverages a topology-aware hypernetwork to act as a bridge that can automatically balance and digest the two heterogeneity patterns in a communication-efficient manner. Our experiments on four AMFL simulations demonstrate the efficiency and effectiveness of our proposed approach.
APA
Chen, J. & Zhang, A.. (2024). FedMBridge: Bridgeable Multimodal Federated Learning. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:7667-7686 Available from https://proceedings.mlr.press/v235/chen24ba.html.

Related Material