Metraipolis › archive › dc_b6b449e45ea9
FlexiFlow: Bandit-based Model Switching in ML Workflows — arXiv:2610.07286
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07286
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:20:29.445Z
- SHA-256 of the archived text
94bdd09b0aae6d46a12447826d24a6b864c9c76b32c7f0a1eb65b7bfe45e3408- Stable URL of this page
https://metraipolis.com/documento/dc_b6b449e45ea9
How to cite
FlexiFlow: Bandit-based Model Switching in ML Workflows — arXiv:2610.07286 — arXiv (en), https://arxiv.org/abs/2610.07286 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6b449e45ea9 (Metraipolis archive dc_b6b449e45ea9, sha256 94bdd09b0aae6d46a12447826d24a6b864c9c76b32c7f0a1eb65b7bfe45e3408)
BibTeX
@misc{dcb6b449e45ea9,
title = {FlexiFlow: Bandit-based Model Switching in ML Workflows — arXiv:2610.07286},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07286},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6b449e45ea9; sha256 94bdd09b0aae6d46a12447826d24a6b864c9c76b32c7f0a1eb65b7bfe45e3408},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07286. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Model optimizations help improve inference performance and accuracy of ML workflows. However, relying on a single model to perform inference across all data batches often fails to maximize accuracy and thus overall performance. In many cases, alternate models could perform better on specific subsets of data where a primary model underperforms. Our experiments with real ML workflows indeed show that switching models improves workflow accuracy by up to 23%. Yet, current systems lack the ability to adaptively switch between models based on performance, forcing users to manually test models in sequence. We present FlexiFlow, a dataflow system that dynamically switches between alternate models when the current model exhibits low accuracy. FlexiFlow learns to rank models using a novel multi-armed bandit approach that accounts for model runtimes, probability of passing user-defined assertions, and the computational structure of the ML workflow. We show that the standard Thompson sampling approach is insufficient for switching models in ML workflows. In contrast, our proposed approaches are effective and scales to complex real-world ML workflows. Experiments show that switching models at runtime while reusing intermediate results provides higher accuracy, but also 48% efficiency gain compared to sequential workflow runs. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.07286 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.695Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).