Context-Aware REpresentation: Jointly learning item features and selection from triplets

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...

Full description

Saved in:
Bibliographic Details
Main Authors: ALVES, Rodrigo, LEDENT, Antoine
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2024
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/9307
https://ink.library.smu.edu.sg/context/sis_research/article/10307/viewcontent/Full_with_appendix.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-10307
record_format dspace
spelling sg-smu-ink.sis_research-103072024-09-21T15:28:33Z Context-Aware REpresentation: Jointly learning item features and selection from triplets ALVES, Rodrigo LEDENT, Antoine 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. 2024-04-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/9307 info:doi/10.1109/TNNLS.2024.3383246 https://ink.library.smu.edu.sg/context/sis_research/article/10307/viewcontent/Full_with_appendix.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Triplets Triplet Loss Item Profiling Interpretability Learning Theory Databases and Information Systems OS and Networks
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Triplets
Triplet Loss
Item Profiling
Interpretability
Learning Theory
Databases and Information Systems
OS and Networks
spellingShingle Triplets
Triplet Loss
Item Profiling
Interpretability
Learning Theory
Databases and Information Systems
OS and Networks
ALVES, Rodrigo
LEDENT, Antoine
Context-Aware REpresentation: Jointly learning item features and selection from triplets
description 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.
format text
author ALVES, Rodrigo
LEDENT, Antoine
author_facet ALVES, Rodrigo
LEDENT, Antoine
author_sort ALVES, Rodrigo
title Context-Aware REpresentation: Jointly learning item features and selection from triplets
title_short Context-Aware REpresentation: Jointly learning item features and selection from triplets
title_full Context-Aware REpresentation: Jointly learning item features and selection from triplets
title_fullStr Context-Aware REpresentation: Jointly learning item features and selection from triplets
title_full_unstemmed Context-Aware REpresentation: Jointly learning item features and selection from triplets
title_sort context-aware representation: jointly learning item features and selection from triplets
publisher Institutional Knowledge at Singapore Management University
publishDate 2024
url https://ink.library.smu.edu.sg/sis_research/9307
https://ink.library.smu.edu.sg/context/sis_research/article/10307/viewcontent/Full_with_appendix.pdf
_version_ 1814047876493344768