MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Ruixiang, Liu, Lingbo, Chen, Changwen
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915616897630208
author Jiang, Ruixiang
Liu, Lingbo
Chen, Changwen
author_facet Jiang, Ruixiang
Liu, Lingbo
Chen, Changwen
contents Despite the demonstrated parameter efficiency of prompt-based fusion, its limited adaptivity and expressiveness hinder its effectiveness for multimodal applications at scale. In this paper, we present the first comprehensive study addressing these limitations. Our key motivation is to ``divide and conquer'' the vanilla prompt, traditionally shared across all instances, by generating instance-specific prompts. Specifically, we propose the Mixture of Prompt Experts (MoPE), a framework that significantly enhances prompt adaptivity and expressiveness by dynamically generating instance-specific prompts. MoPE leverages multimodal pairings as additional evidence, allowing the model to adaptively select optimal prompts tailored to each individual instance. Unlike traditional prompt-fusion methods, which encounter scalability bottlenecks when optimizing long unified prompts, MoPE maintains fixed prompt length while effectively scaling the number of specialized experts. Moreover, we investigate regularization terms to encourage expert specialization, resulting in highly adaptive and interpretable prompting. MoPE fundamentally changes the scaling dynamic, unlocking greater expressiveness and adaptability to complex multimodal relationships, enabling the model to selectively attend to task-relevant sub-sequences based on instance-specific multimodal input. Extensive experiments across six multimodal datasets spanning four modalities demonstrate state-of-the-art performance for multimodal fusion, matching or surpassing the performance of fine-tuning while requiring only 0.8% of the trainable parameters. Code is available: https://github.com/songrise/MoPE.
format Preprint
id arxiv_https___arxiv_org_abs_2403_10568
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
Jiang, Ruixiang
Liu, Lingbo
Chen, Changwen
Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
Despite the demonstrated parameter efficiency of prompt-based fusion, its limited adaptivity and expressiveness hinder its effectiveness for multimodal applications at scale. In this paper, we present the first comprehensive study addressing these limitations. Our key motivation is to ``divide and conquer'' the vanilla prompt, traditionally shared across all instances, by generating instance-specific prompts. Specifically, we propose the Mixture of Prompt Experts (MoPE), a framework that significantly enhances prompt adaptivity and expressiveness by dynamically generating instance-specific prompts. MoPE leverages multimodal pairings as additional evidence, allowing the model to adaptively select optimal prompts tailored to each individual instance. Unlike traditional prompt-fusion methods, which encounter scalability bottlenecks when optimizing long unified prompts, MoPE maintains fixed prompt length while effectively scaling the number of specialized experts. Moreover, we investigate regularization terms to encourage expert specialization, resulting in highly adaptive and interpretable prompting. MoPE fundamentally changes the scaling dynamic, unlocking greater expressiveness and adaptability to complex multimodal relationships, enabling the model to selectively attend to task-relevant sub-sequences based on instance-specific multimodal input. Extensive experiments across six multimodal datasets spanning four modalities demonstrate state-of-the-art performance for multimodal fusion, matching or surpassing the performance of fine-tuning while requiring only 0.8% of the trainable parameters. Code is available: https://github.com/songrise/MoPE.
title MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion
topic Machine Learning
Artificial Intelligence
Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.10568