Graph Convolutional Embeddings for Recommender Systems
Modern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9481221/ |
| _version_ | 1818741455824355328 |
|---|---|
| author | Paula G. Duran Alexandros Karatzoglou Jordi Vitria Xin Xin Ioannis Arapakis |
| author_facet | Paula G. Duran Alexandros Karatzoglou Jordi Vitria Xin Xin Ioannis Arapakis |
| author_sort | Paula G. Duran |
| collection | DOAJ |
| description | Modern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of signals like the context of interactions, which could be, for example, the time or date of the interaction, the user location, or sequential data corresponding to the historical interactions of the user with the system. These complex, context-based interaction signals are characterized by a rich relational structure that can be represented by a multi-partite graph. Graph Convolutional Networks (GCNs) have been used successfully in collaborative filtering with simple user-item interaction data. In this work, we generalize the use of GCNs for N-partite graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures. More specifically, we define a graph convolutional embedding layer for N-partite graphs that processes user-item-context interactions and constructs node embeddings by leveraging their relational structure. Experiments on several datasets show the benefits of the introduced GCN embedding layer by measuring the performance of different context-enriched tasks. |
| first_indexed | 2024-12-18T01:56:54Z |
| format | Article |
| id | doaj.art-6f847c6fa75e4a66a8b888cfb9677080 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T01:56:54Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-6f847c6fa75e4a66a8b888cfb96770802022-12-21T21:24:54ZengIEEEIEEE Access2169-35362021-01-01910017310018410.1109/ACCESS.2021.30966099481221Graph Convolutional Embeddings for Recommender SystemsPaula G. Duran0https://orcid.org/0000-0003-4858-4386Alexandros Karatzoglou1Jordi Vitria2https://orcid.org/0000-0003-1484-539XXin Xin3Ioannis Arapakis4Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, SpainGoogle Research, London, N1C, U.K.Departament de Matemàtiques i Informàtica, Universitat de Barcelona, Barcelona, SpainSchool of Computing Science, University of Glasgow, Glasgow, U.K.Telefonica Research, Barcelona, SpainModern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of signals like the context of interactions, which could be, for example, the time or date of the interaction, the user location, or sequential data corresponding to the historical interactions of the user with the system. These complex, context-based interaction signals are characterized by a rich relational structure that can be represented by a multi-partite graph. Graph Convolutional Networks (GCNs) have been used successfully in collaborative filtering with simple user-item interaction data. In this work, we generalize the use of GCNs for N-partite graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures. More specifically, we define a graph convolutional embedding layer for N-partite graphs that processes user-item-context interactions and constructs node embeddings by leveraging their relational structure. Experiments on several datasets show the benefits of the introduced GCN embedding layer by measuring the performance of different context-enriched tasks.https://ieeexplore.ieee.org/document/9481221/Graph convolutional networkinteraction contextembedding layerfactorization machinesneural networkscollaborative filtering |
| spellingShingle | Paula G. Duran Alexandros Karatzoglou Jordi Vitria Xin Xin Ioannis Arapakis Graph Convolutional Embeddings for Recommender Systems IEEE Access Graph convolutional network interaction context embedding layer factorization machines neural networks collaborative filtering |
| title | Graph Convolutional Embeddings for Recommender Systems |
| title_full | Graph Convolutional Embeddings for Recommender Systems |
| title_fullStr | Graph Convolutional Embeddings for Recommender Systems |
| title_full_unstemmed | Graph Convolutional Embeddings for Recommender Systems |
| title_short | Graph Convolutional Embeddings for Recommender Systems |
| title_sort | graph convolutional embeddings for recommender systems |
| topic | Graph convolutional network interaction context embedding layer factorization machines neural networks collaborative filtering |
| url | https://ieeexplore.ieee.org/document/9481221/ |
| work_keys_str_mv | AT paulagduran graphconvolutionalembeddingsforrecommendersystems AT alexandroskaratzoglou graphconvolutionalembeddingsforrecommendersystems AT jordivitria graphconvolutionalembeddingsforrecommendersystems AT xinxin graphconvolutionalembeddingsforrecommendersystems AT ioannisarapakis graphconvolutionalembeddingsforrecommendersystems |