Multiview Representation Learning from Crowdsourced Triplet Comparisons

TL;DR

This paper introduces an end-to-end deep learning framework for multiview representation learning from crowdsourced triplet comparisons, enabling independent prediction of multiple attribute-based embeddings for objects.

Contribution

It presents a novel inductive deep learning method that addresses limitations of prior algorithms by allowing independent multiview embedding prediction and accommodating view preferences.

Findings

The proposed method effectively learns multiview embeddings from crowdsourced data.

Experimental results show improved performance over baseline methods.

The approach can generate embeddings for new objects in any view.

Abstract

Crowdsourcing has been used to collect data at scale in numerous fields. Triplet similarity comparison is a type of crowdsourcing task, in which crowd workers are asked the question ``among three given objects, which two are more similar?'', which is relatively easy for humans to answer. However, the comparison can be sometimes based on multiple views, i.e., different independent attributes such as color and shape. Each view may lead to different results for the same three objects. Although an algorithm was proposed in prior work to produce multiview embeddings, it involves at least two problems: (1) the existing algorithm cannot independently predict multiview embeddings for a new sample, and (2) different people may prefer different views. In this study, we propose an end-to-end inductive deep learning framework to solve the multiview representation learning problem. The results show that our proposed method can obtain multiview embeddings of any object, in which each view corresponds to an independent attribute of the object. We collected two datasets from a crowdsourcing platform to experimentally investigate the performance of our proposed approach compared to conventional baseline methods.