Context-Aware REpresentation: Jointly Learning Item Features and Selection From Triplets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F25%3A00383450" target="_blank" >RIV/68407700:21240/25:00383450 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/TNNLS.2024.3383246" target="_blank" >https://doi.org/10.1109/TNNLS.2024.3383246</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TNNLS.2024.3383246" target="_blank" >10.1109/TNNLS.2024.3383246</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Context-Aware REpresentation: Jointly Learning Item Features and Selection From Triplets

Popis výsledku v původním jazyce

In areas of machine learning such as cognitive modeling or recommendation, user feedback is usually context-dependent. For instance, a website might provide a user with a set of recommendations and observe which (if any) of the links were clicked by the user. Similarly, there is growing interest in the so-called “odd-one-out” learning setting, where human participants are provided with a basket of items and asked which is the most dissimilar to the others. In both of those cases, the presence of all the items in the basket can influence the final decision. In this article, we consider a classification task where each input consists of three items (a triplet), and the task is to predict which of the three will be selected. Our aim is not only to return accurate predictions for the selection task, but also to additionally provide interpretable feature representations for both the context and for each individual item. To achieve this, we introduce CARE, a specialized neural network architecture that yields Context-Aware REpresentations of items based on observations of triplets of items alone. We demonstrate that, in addition to achieving state-of-the-art performance at the selection task, our model can produce meaningful representations both for each item, as well for each context (triplet of items). This is done using only triplet responses: CARE has no access to supervised item-level information. In addition, we prove parameter counting generalization bounds for our model in the i.i.d. setting, demonstrating that the apparent sample sparsity arising from the combinatorially large number of possible triplets is no obstacle to efficient learning.

Název v anglickém jazyce

Context-Aware REpresentation: Jointly Learning Item Features and Selection From Triplets

Popis výsledku anglicky

In areas of machine learning such as cognitive modeling or recommendation, user feedback is usually context-dependent. For instance, a website might provide a user with a set of recommendations and observe which (if any) of the links were clicked by the user. Similarly, there is growing interest in the so-called “odd-one-out” learning setting, where human participants are provided with a basket of items and asked which is the most dissimilar to the others. In both of those cases, the presence of all the items in the basket can influence the final decision. In this article, we consider a classification task where each input consists of three items (a triplet), and the task is to predict which of the three will be selected. Our aim is not only to return accurate predictions for the selection task, but also to additionally provide interpretable feature representations for both the context and for each individual item. To achieve this, we introduce CARE, a specialized neural network architecture that yields Context-Aware REpresentations of items based on observations of triplets of items alone. We demonstrate that, in addition to achieving state-of-the-art performance at the selection task, our model can produce meaningful representations both for each item, as well for each context (triplet of items). This is done using only triplet responses: CARE has no access to supervised item-level information. In addition, we prove parameter counting generalization bounds for our model in the i.i.d. setting, demonstrating that the apparent sample sparsity arising from the combinatorially large number of possible triplets is no obstacle to efficient learning.

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

IEEE Transactions on Neural Networks and Learning Systems

ISSN

2162-237X

e-ISSN

2162-2388

Svazek periodika

36

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

11

Strana od-do

6492-6502

Kód UT WoS článku

001201951900001

EID výsledku v databázi Scopus

2-s2.0-105002402483