File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Inductive Contextual Relation Learning for Personalization

TitleInductive Contextual Relation Learning for Personalization
Authors
Keywordscontent-based recommendation
node embedding
Personalization
relation learning
Issue Date2021
Citation
ACM Transactions on Information Systems, 2021, v. 39, n. 3, article no. 35 How to Cite?
AbstractWeb personalization, e.g., recommendation or relevance search, tailoring a service/product to accommodate specific online users, is becoming increasingly important. Inductive personalization aims to infer the relations between existing entities and unseen new ones, e.g., searching relevant authors for new papers or recommending new items to users. This problem, however, is challenging since most of recent studies focus on transductive problem for existing entities. In addition, despite some inductive learning approaches have been introduced recently, their performance is sub-optimal due to relatively simple and inflexible architectures for aggregating entity's content. To this end, we propose the inductive contextual personalization (ICP) framework through contextual relation learning. Specifically, we first formulate the pairwise relations between entities with a ranking optimization scheme that employs neural aggregator to fuse entity's heterogeneous contents. Next, we introduce a node embedding term to capture entity's contextual relations, as a smoothness constraint over the prior ranking objective. Finally, the gradient descent procedure with adaptive negative sampling is employed to learn the model parameters. The learned model is capable of inferring the relations between existing entities and inductive ones. Thorough experiments demonstrate that ICP outperforms numerous baseline methods for two different applications, i.e., relevant author search and new item recommendation.
Persistent Identifierhttp://hdl.handle.net/10722/308685
ISSN
2023 Impact Factor: 5.4
2023 SCImago Journal Rankings: 2.262
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Chuxu-
dc.contributor.authorYao, Huaxiu-
dc.contributor.authorYu, Lu-
dc.contributor.authorHuang, Chao-
dc.contributor.authorSong, Dongjin-
dc.contributor.authorChen, Haifeng-
dc.contributor.authorJiang, Meng-
dc.contributor.authorChawla, Nitesh V.-
dc.date.accessioned2021-12-08T07:49:55Z-
dc.date.available2021-12-08T07:49:55Z-
dc.date.issued2021-
dc.identifier.citationACM Transactions on Information Systems, 2021, v. 39, n. 3, article no. 35-
dc.identifier.issn1046-8188-
dc.identifier.urihttp://hdl.handle.net/10722/308685-
dc.description.abstractWeb personalization, e.g., recommendation or relevance search, tailoring a service/product to accommodate specific online users, is becoming increasingly important. Inductive personalization aims to infer the relations between existing entities and unseen new ones, e.g., searching relevant authors for new papers or recommending new items to users. This problem, however, is challenging since most of recent studies focus on transductive problem for existing entities. In addition, despite some inductive learning approaches have been introduced recently, their performance is sub-optimal due to relatively simple and inflexible architectures for aggregating entity's content. To this end, we propose the inductive contextual personalization (ICP) framework through contextual relation learning. Specifically, we first formulate the pairwise relations between entities with a ranking optimization scheme that employs neural aggregator to fuse entity's heterogeneous contents. Next, we introduce a node embedding term to capture entity's contextual relations, as a smoothness constraint over the prior ranking objective. Finally, the gradient descent procedure with adaptive negative sampling is employed to learn the model parameters. The learned model is capable of inferring the relations between existing entities and inductive ones. Thorough experiments demonstrate that ICP outperforms numerous baseline methods for two different applications, i.e., relevant author search and new item recommendation.-
dc.languageeng-
dc.relation.ispartofACM Transactions on Information Systems-
dc.subjectcontent-based recommendation-
dc.subjectnode embedding-
dc.subjectPersonalization-
dc.subjectrelation learning-
dc.titleInductive Contextual Relation Learning for Personalization-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1145/3450353-
dc.identifier.scopuseid_2-s2.0-85119096804-
dc.identifier.volume39-
dc.identifier.issue3-
dc.identifier.spagearticle no. 35-
dc.identifier.epagearticle no. 35-
dc.identifier.eissn1558-2868-
dc.identifier.isiWOS:000717303100014-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats