MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning

Uloženo v:

Podrobná bibliografie
Vydáno v:	arXiv.org (Dec 24, 2024), p. n/a
Hlavní autor:	Chergui, Abdelmadjid
Další autoři:	Bezirganyan, Grigor, Sellami, Sana, Berti-Équille, Laure, Fournier, Sébastien
Vydáno:	Cornell University Library, arXiv.org
Témata:	Performance measurement Data integration Deep learning Machine learning Data search Sampling
On-line přístup:	Citation/Abstract Full text outside of ProQuest
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Abstrakt:	Choosing a suitable deep learning architecture for multimodal data fusion is a challenging task, as it requires the effective integration and processing of diverse data types, each with distinct structures and characteristics. In this paper, we introduce MixMAS, a novel framework for sampling-based mixer architecture search tailored to multimodal learning. Our approach automatically selects the optimal MLP-based architecture for a given multimodal machine learning (MML) task. Specifically, MixMAS utilizes a sampling-based micro-benchmarking strategy to explore various combinations of modality-specific encoders, fusion functions, and fusion networks, systematically identifying the architecture that best meets the task's performance metrics.
ISSN:	2331-8422
Zdroj:	Engineering Database