Saved in:
Bibliographic Details
Main Authors: Varshneya, Saurabh, Ledent, Antoine, Liznerski, Philipp, Balinskyy, Andriy, Mehta, Purvanshi, Mustafa, Waleed, Kloft, Marius
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.04671
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917661138485248
author Varshneya, Saurabh
Ledent, Antoine
Liznerski, Philipp
Balinskyy, Andriy
Mehta, Purvanshi
Mustafa, Waleed
Kloft, Marius
author_facet Varshneya, Saurabh
Ledent, Antoine
Liznerski, Philipp
Balinskyy, Andriy
Mehta, Purvanshi
Mustafa, Waleed
Kloft, Marius
contents Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method for training neural networks to simultaneously learn multimodal data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of diverse data types, thereby disentangling higher-order interactions from the individual effects of each modality. InTense provides interpretability out of the box by assigning relevance scores to modalities and their associations. The approach is theoretically grounded and yields meaningful relevance scores on multiple synthetic and real-world datasets. Experiments on six real-world datasets show that InTense outperforms existing state-of-the-art multimodal interpretable approaches in terms of accuracy and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04671
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Interpretable Tensor Fusion
Varshneya, Saurabh
Ledent, Antoine
Liznerski, Philipp
Balinskyy, Andriy
Mehta, Purvanshi
Mustafa, Waleed
Kloft, Marius
Machine Learning
Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce interpretable tensor fusion (InTense), a multimodal learning method for training neural networks to simultaneously learn multimodal data representations and their interpretable fusion. InTense can separately capture both linear combinations and multiplicative interactions of diverse data types, thereby disentangling higher-order interactions from the individual effects of each modality. InTense provides interpretability out of the box by assigning relevance scores to modalities and their associations. The approach is theoretically grounded and yields meaningful relevance scores on multiple synthetic and real-world datasets. Experiments on six real-world datasets show that InTense outperforms existing state-of-the-art multimodal interpretable approaches in terms of accuracy and interpretability.
title Interpretable Tensor Fusion
topic Machine Learning
url https://arxiv.org/abs/2405.04671