analiza aiqbench
MetaSE introduces a stateful active ensemble framework that optimizes mobile sensing by maintaining a small set of reliable models while dynamically rejecting unreliable ones based on short-term persistence. This approach significantly reduces computational overhead and memory usage on edge devices like the Raspberry Pi 4B without sacrificing accuracy compared to full-ensemble inference. The method effectively balances robustness and efficiency, addressing the high cost of repeatedly executing multiple models over continuous sensor streams.
Metacognitive Selective Ensemble for Mobile Systems
arXiv:2609.31031v1 Announce Type: new Abstract: Deep ensembles improve robustness in mobile sensing, but repeatedly executing many models over continuous sensor streams is costly. Selecting only a few members reduces this cost, yet adaptive selection often requires additional model execution to obtain reliable evidence about inactive candidates. We present MetaSE, an active ensemble framework that exploits short-term persistence in per-model reliability. MetaSE maintains a small active set across windows, uses post-execution evidence to reject unreliable members, and invokes lightweight routing only when replacement is needed. This stateful design accesses the diversity of a larger pool without repeated full-pool evaluation. Across four HAR datasets and four model architectures, MetaSE consistently improves over a fixed three-model ensemble and achieves accuracy comparable to substantially more expensive adaptive and full-ensemble inference. On a Raspberry Pi 4B, MetaSE is 2.7x faster and uses 69% less memory than full ten-model inference.
Abstract:Deep ensembles improve robustness in mobile sensing, but repeatedly executing many models over continuous sensor streams is costly. Selecting only a few members reduces this cost, yet adaptive selection often requires additional model execution to obtain reliable evidence about inactive candidates. We present MetaSE, an active ensemble framework that exploits short-term persistence in per-model reliability. MetaSE maintains a small active set across windows, uses post-execution evidence to reject unreliable members, and invokes lightweight routing only when replacement is needed. This stateful design accesses the diversity of a larger pool without repeated full-pool evaluation. Across four HAR datasets and four model architectures, MetaSE consistently improves over a fixed three-model ensemble and achieves accuracy comparable to substantially more expensive adaptive and full-ensemble inference. On a Raspberry Pi 4B, MetaSE is 2.7x faster and uses 69% less memory than full ten-model inference.
Machine Learning (cs.LG)
arXiv:2609.31031 [cs.LG]
(or arXiv:2609.31031v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.31031 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 233 cuvinte
Subiecte conexe
Game-Theoretic Disempowerment: Loss of Control to Agencyless AI
LessWrong · 27 sept. 2026
University of Connecticut Perturbative Theory Predicts Plateau Height & Timescale
Quantum Zeitgeist · 16 aug. 2026
Implementation of a Metacognition Framework for Self-Awareness and Self-Regulation in Ensembles of LLMs
arXiv · 18 aug. 2026
TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation Models
arXiv · 12 iun. 2026