Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender Systems
Despite many recent advances, state-of-the-art recommender systems still struggle to achieve good performance with sparse datasets. To address the sparsity issue, transfer learning techniques have been investigated for recommender systems, but they tend to impose strict constraints on the content an...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9815228/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841554063896870912 |
|---|---|
| author | Qinqin Wang Diarmuid Oreilly-Morgan Elias Z. Tragos Neil Hurley Barry Smyth Aonghus Lawlor Ruihai Dong |
| author_facet | Qinqin Wang Diarmuid Oreilly-Morgan Elias Z. Tragos Neil Hurley Barry Smyth Aonghus Lawlor Ruihai Dong |
| author_sort | Qinqin Wang |
| collection | DOAJ |
| description | Despite many recent advances, state-of-the-art recommender systems still struggle to achieve good performance with sparse datasets. To address the sparsity issue, transfer learning techniques have been investigated for recommender systems, but they tend to impose strict constraints on the content and structure of the data in the source and target domains. For transfer learning methods to work well, there should normally be homogeneity between source and target domains, or a high degree of overlap between the source and target items. In this paper we propose a novel transfer learning framework for mitigating the effects of sparsity and insufficient data. Our method requires neither homogeneity nor overlap between the source and target domains. We describe and evaluate a shared parameter auto-encoder to jointly learn representations of user/item aspects in two domains, applying Maximum Mean Discrepancy (MMD) loss during training to ensure that the source and target representations are similar in the distribution space. The approach is evaluated using a number of benchmark datasets to demonstrate improved recommendation performance when learned representations are used in collaborative filtering. The code used for this work is available on github.com. |
| format | Article |
| id | doaj-art-c268e01f9598415e8e0eef74e399636d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-c268e01f9598415e8e0eef74e399636d2025-01-09T00:00:36ZengIEEEIEEE Access2169-35362022-01-0110719617197210.1109/ACCESS.2022.31887099815228Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender SystemsQinqin Wang0Diarmuid Oreilly-Morgan1Elias Z. Tragos2https://orcid.org/0000-0001-9566-531XNeil Hurley3Barry Smyth4Aonghus Lawlor5https://orcid.org/0000-0002-6160-4639Ruihai Dong6https://orcid.org/0000-0002-2509-1370Insight Centre for Data Analytics, University College Dublin, Dublin 4, Belfield, IrelandInsight Centre for Data Analytics, University College Dublin, Dublin 4, Belfield, IrelandInsight Centre for Data Analytics, University College Dublin, Dublin 4, Belfield, IrelandInsight Centre for Data Analytics, University College Dublin, Dublin 4, Belfield, IrelandInsight Centre for Data Analytics, University College Dublin, Dublin 4, Belfield, IrelandInsight Centre for Data Analytics, University College Dublin, Dublin 4, Belfield, IrelandInsight Centre for Data Analytics, University College Dublin, Dublin 4, Belfield, IrelandDespite many recent advances, state-of-the-art recommender systems still struggle to achieve good performance with sparse datasets. To address the sparsity issue, transfer learning techniques have been investigated for recommender systems, but they tend to impose strict constraints on the content and structure of the data in the source and target domains. For transfer learning methods to work well, there should normally be homogeneity between source and target domains, or a high degree of overlap between the source and target items. In this paper we propose a novel transfer learning framework for mitigating the effects of sparsity and insufficient data. Our method requires neither homogeneity nor overlap between the source and target domains. We describe and evaluate a shared parameter auto-encoder to jointly learn representations of user/item aspects in two domains, applying Maximum Mean Discrepancy (MMD) loss during training to ensure that the source and target representations are similar in the distribution space. The approach is evaluated using a number of benchmark datasets to demonstrate improved recommendation performance when learned representations are used in collaborative filtering. The code used for this work is available on github.com.https://ieeexplore.ieee.org/document/9815228/Recommender systemneural networkstransfer learningdomain adaptation |
| spellingShingle | Qinqin Wang Diarmuid Oreilly-Morgan Elias Z. Tragos Neil Hurley Barry Smyth Aonghus Lawlor Ruihai Dong Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender Systems IEEE Access Recommender system neural networks transfer learning domain adaptation |
| title | Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender Systems |
| title_full | Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender Systems |
| title_fullStr | Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender Systems |
| title_full_unstemmed | Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender Systems |
| title_short | Learning Domain-Independent Representations via Shared Weight Auto-Encoder for Transfer Learning in Recommender Systems |
| title_sort | learning domain independent representations via shared weight auto encoder for transfer learning in recommender systems |
| topic | Recommender system neural networks transfer learning domain adaptation |
| url | https://ieeexplore.ieee.org/document/9815228/ |
| work_keys_str_mv | AT qinqinwang learningdomainindependentrepresentationsviasharedweightautoencoderfortransferlearninginrecommendersystems AT diarmuidoreillymorgan learningdomainindependentrepresentationsviasharedweightautoencoderfortransferlearninginrecommendersystems AT eliasztragos learningdomainindependentrepresentationsviasharedweightautoencoderfortransferlearninginrecommendersystems AT neilhurley learningdomainindependentrepresentationsviasharedweightautoencoderfortransferlearninginrecommendersystems AT barrysmyth learningdomainindependentrepresentationsviasharedweightautoencoderfortransferlearninginrecommendersystems AT aonghuslawlor learningdomainindependentrepresentationsviasharedweightautoencoderfortransferlearninginrecommendersystems AT ruihaidong learningdomainindependentrepresentationsviasharedweightautoencoderfortransferlearninginrecommendersystems |