ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation
As Massive Open Online Courses (MOOCs) expand and diversify, more and more researchers study recommender systems that take advantage of interaction data to keep students interested and boost their performance. In a typical roadmap, courses and videos are recommended using a graph model, but this d...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Institute of Electrical and Electronics Engineers
2023
|
| _version_ | 1811137886517460992 |
|---|---|
| author | Luo, Hao Husin, Nor Azura Mohd Aris, Teh Noranis |
| author_facet | Luo, Hao Husin, Nor Azura Mohd Aris, Teh Noranis |
| author_sort | Luo, Hao |
| collection | UPM |
| description | As Massive Open Online Courses (MOOCs) expand and diversify, more and more researchers
study recommender systems that take advantage of interaction data to keep students interested and boost their
performance. In a typical roadmap, courses and videos are recommended using a graph model, but this does
not take into account the user’s learning needs with some particular subjects. However, all existing graph
models degrade performances either by ignoring the data sparsity issue caused by a large number of concepts,
which may lead to biased recommendations, or by constructing improper contrasting pairs, which may
result in graph noise. To overcome both challenges, we propose a gRaph cOntrastive Multi-view framEwork
(ROME) from hyperbolic angular space to learn user and concept representations based on user-user and
concept-concept relationships. The first step is to use hyperbolic and Euclidean space representations as
different views of graph and maximize the mutual information between them. Furthermore, we maximize
the angular decision margin in graph contrastive training objects to enhance pairwise discriminative power.
Our experiments on a large-scale real-world MOOC dataset show that the proposed approach outperforms
several baselines and state-of-the-art methods for predicting and recommending concepts of interest to users. |
| first_indexed | 2024-09-25T03:41:25Z |
| format | Article |
| id | upm.eprints-109167 |
| institution | Universiti Putra Malaysia |
| last_indexed | 2024-09-25T03:41:25Z |
| publishDate | 2023 |
| publisher | Institute of Electrical and Electronics Engineers |
| record_format | dspace |
| spelling | upm.eprints-1091672024-08-27T04:54:34Z http://psasir.upm.edu.my/id/eprint/109167/ ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation Luo, Hao Husin, Nor Azura Mohd Aris, Teh Noranis As Massive Open Online Courses (MOOCs) expand and diversify, more and more researchers study recommender systems that take advantage of interaction data to keep students interested and boost their performance. In a typical roadmap, courses and videos are recommended using a graph model, but this does not take into account the user’s learning needs with some particular subjects. However, all existing graph models degrade performances either by ignoring the data sparsity issue caused by a large number of concepts, which may lead to biased recommendations, or by constructing improper contrasting pairs, which may result in graph noise. To overcome both challenges, we propose a gRaph cOntrastive Multi-view framEwork (ROME) from hyperbolic angular space to learn user and concept representations based on user-user and concept-concept relationships. The first step is to use hyperbolic and Euclidean space representations as different views of graph and maximize the mutual information between them. Furthermore, we maximize the angular decision margin in graph contrastive training objects to enhance pairwise discriminative power. Our experiments on a large-scale real-world MOOC dataset show that the proposed approach outperforms several baselines and state-of-the-art methods for predicting and recommending concepts of interest to users. Institute of Electrical and Electronics Engineers 2023 Article PeerReviewed Luo, Hao and Husin, Nor Azura and Mohd Aris, Teh Noranis (2023) ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation. IEEE Access, 11. pp. 9691-9700. ISSN 2169-3536 https://ieeexplore.ieee.org/document/10001755/ 10.1109/access.2022.3232552 |
| spellingShingle | Luo, Hao Husin, Nor Azura Mohd Aris, Teh Noranis ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation |
| title | ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation |
| title_full | ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation |
| title_fullStr | ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation |
| title_full_unstemmed | ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation |
| title_short | ROME: a graph contrastive multi-view framework from hyperbolic angular space for MOOCs recommendation |
| title_sort | rome a graph contrastive multi view framework from hyperbolic angular space for moocs recommendation |
| work_keys_str_mv | AT luohao romeagraphcontrastivemultiviewframeworkfromhyperbolicangularspaceformoocsrecommendation AT husinnorazura romeagraphcontrastivemultiviewframeworkfromhyperbolicangularspaceformoocsrecommendation AT mohdaristehnoranis romeagraphcontrastivemultiviewframeworkfromhyperbolicangularspaceformoocsrecommendation |