Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chergui, Abdelmadjid, Bezirganyan, Grigor, Sellami, Sana, Berti-Équille, Laure, Fournier, Sébastien
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.18437
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910791789182976
author Chergui, Abdelmadjid
Bezirganyan, Grigor
Sellami, Sana
Berti-Équille, Laure
Fournier, Sébastien
author_facet Chergui, Abdelmadjid
Bezirganyan, Grigor
Sellami, Sana
Berti-Équille, Laure
Fournier, Sébastien
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18437
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning
Chergui, Abdelmadjid
Bezirganyan, Grigor
Sellami, Sana
Berti-Équille, Laure
Fournier, Sébastien
Machine Learning
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.
title MixMAS: A Framework for Sampling-Based Mixer Architecture Search for Multimodal Fusion and Learning
topic Machine Learning
url https://arxiv.org/abs/2412.18437