Multitask learning for cognitive sciences triplet analysis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F25%3A00382223" target="_blank" >RIV/68407700:21240/25:00382223 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1016/j.eswa.2024.126187" target="_blank" >https://doi.org/10.1016/j.eswa.2024.126187</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.eswa.2024.126187" target="_blank" >10.1016/j.eswa.2024.126187</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Multitask learning for cognitive sciences triplet analysis

Popis výsledku v původním jazyce

The triplet-based odd-one-out problem, which involves trials where human subjects are asked to select the most different concept among three, is a well-studied task in cognitive sciences. With the release of a large triplet-based dataset, THINGS, there has been a recent surge in the popularity of machine learning models aimed at learning mathematical representations of object concepts, such as SPoSE, VICE, and CARE. The first two models learn representations by maximizing the similarity between the two most similar objects, while the latter diverges by directly learning the odd-one-out, making its embedding more distant. No prior attempts have integrated both paradigms, which are important for understanding object representation in cognitive science. In this paper, we propose MASTER, a multitask learning method for the triplet problem that encapsulates both paradigms. Our results demonstrate that our method not only better predicts the odd-one-out object but also provides insightful representations for studying these concepts. Furthermore, we studied the conditions under which each model performs better, offering valuable insights for future research on how these paradigms affect human understanding of object concepts.

Název v anglickém jazyce

Multitask learning for cognitive sciences triplet analysis

Popis výsledku anglicky

The triplet-based odd-one-out problem, which involves trials where human subjects are asked to select the most different concept among three, is a well-studied task in cognitive sciences. With the release of a large triplet-based dataset, THINGS, there has been a recent surge in the popularity of machine learning models aimed at learning mathematical representations of object concepts, such as SPoSE, VICE, and CARE. The first two models learn representations by maximizing the similarity between the two most similar objects, while the latter diverges by directly learning the odd-one-out, making its embedding more distant. No prior attempts have integrated both paradigms, which are important for understanding object representation in cognitive science. In this paper, we propose MASTER, a multitask learning method for the triplet problem that encapsulates both paradigms. Our results demonstrate that our method not only better predicts the odd-one-out object but also provides insightful representations for studying these concepts. Furthermore, we studied the conditions under which each model performs better, offering valuable insights for future research on how these paradigms affect human understanding of object concepts.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Expert Systems with Applications

ISSN

0957-4174

e-ISSN

1873-6793

Svazek periodika

267

Číslo periodika v rámci svazku

126187

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

10

Strana od-do

1-10

Kód UT WoS článku

001392960000001

EID výsledku v databázi Scopus

2-s2.0-85212554744