PhyMask: An Adaptive Masking Paradigm for Efficient Self-Supervised Learning in IoT

D Kara, T Kimura, Y Chen, J Li, R Wang… - Proceedings of the …, 2024 - dl.acm.org
This paper introduces PhyMask, an adaptive masking paradigm designed to enhance the
efficiency and interpretability of Masked Autoencoders (MAEs) in analyzing IoT sensing …

The Case for Micro Foundation Models to Support Robust Edge Intelligence

T Kimura, A Misra, Y Chen, D Kara, J Li… - 2024 IEEE 6th …, 2024 - ieeexplore.ieee.org
This paper advocates the concept of micro foundation models (μFMs), recently introduced by
the authors to describe a category of self-supervised pre-training solutions that we argue are …

Enhancing Resilience in Distributed ML Inference Pipelines for Edge Computing

L Wu, WA Hanafy, A Souza… - MILCOM 2024-2024 …, 2024 - ieeexplore.ieee.org
As edge computing and sensing devices continue to proliferate, distributed machine
learning (ML) inference pipelines are becoming popular for enabling low-latency, real-time …

InfoMAE: Pairing-Efficient Cross-Modal Alignment with Informational Masked Autoencoders for IoT Signals

T Kimura, X Li, O Hanna, Y Chen, Y Chen… - THE WEB … - openreview.net
Standard multimodal self-supervised learning (SSL) algorithms regard cross-modal
synchronization as implicit supervisory labels during pretraining, thus posing high …