File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICDE51399.2021.00084
- WOS: WOS:000687830800077
Supplementary
-
Citations:
- Web of Science: 0
- Appears in Collections:
Conference Paper: Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
Title | Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks |
---|---|
Authors | |
Keywords | Heterogeneous information networks Classification Graph neural networks |
Issue Date | 2021 |
Publisher | IEEE Computer Society. |
Citation | 37th IEEE International Conference on Data Engineering (ICDE 2021) (Online), Chania, Greece, April 19-22, 2021. In 2021 IEEE 37th International Conference on Data Engineering (ICDE), p. 912-923 How to Cite? |
Abstract | A heterogeneous information network (HIN) has as vertices objects of different types and as edges the relations between objects, which are also of various types. We study the problem of classifying objects in HINs. Most existing methods perform poorly when given scarce labeled objects as training sets, and methods that improve classification accuracy under such scenarios are often computationally expensive. To address these problems, we propose ConCH, a graph neural network model. ConCH formulates the classification problem as a multi-task learning problem that combines semi-supervised learning with self-supervised learning to learn from both labeled and unlabeled data. ConCH employs meta-paths, which are sequences of object types that capture semantic relationships between objects. ConCH co-derives object embeddings and context embeddings via graph convolution. It also uses the attention mechanism to fuse such embeddings. We conduct extensive experiments to evaluate the performance of ConCH against other 15 classification methods. Our results show that ConCH is an effective and efficient method for HIN classification. |
Persistent Identifier | http://hdl.handle.net/10722/319920 |
ISBN | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, X | - |
dc.contributor.author | Ding, D | - |
dc.contributor.author | Kao, CM | - |
dc.contributor.author | Sun, Y | - |
dc.contributor.author | Mamoulis, N | - |
dc.date.accessioned | 2022-10-14T05:22:10Z | - |
dc.date.available | 2022-10-14T05:22:10Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | 37th IEEE International Conference on Data Engineering (ICDE 2021) (Online), Chania, Greece, April 19-22, 2021. In 2021 IEEE 37th International Conference on Data Engineering (ICDE), p. 912-923 | - |
dc.identifier.isbn | 9781728191843 | - |
dc.identifier.uri | http://hdl.handle.net/10722/319920 | - |
dc.description.abstract | A heterogeneous information network (HIN) has as vertices objects of different types and as edges the relations between objects, which are also of various types. We study the problem of classifying objects in HINs. Most existing methods perform poorly when given scarce labeled objects as training sets, and methods that improve classification accuracy under such scenarios are often computationally expensive. To address these problems, we propose ConCH, a graph neural network model. ConCH formulates the classification problem as a multi-task learning problem that combines semi-supervised learning with self-supervised learning to learn from both labeled and unlabeled data. ConCH employs meta-paths, which are sequences of object types that capture semantic relationships between objects. ConCH co-derives object embeddings and context embeddings via graph convolution. It also uses the attention mechanism to fuse such embeddings. We conduct extensive experiments to evaluate the performance of ConCH against other 15 classification methods. Our results show that ConCH is an effective and efficient method for HIN classification. | - |
dc.language | eng | - |
dc.publisher | IEEE Computer Society. | - |
dc.relation.ispartof | 2021 IEEE 37th International Conference on Data Engineering (ICDE) | - |
dc.rights | 2021 IEEE 37th International Conference on Data Engineering (ICDE). Copyright © IEEE. | - |
dc.rights | ©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | Heterogeneous information networks | - |
dc.subject | Classification | - |
dc.subject | Graph neural networks | - |
dc.title | Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Kao, CM: kao@cs.hku.hk | - |
dc.identifier.authority | Kao, CM=rp00123 | - |
dc.identifier.doi | 10.1109/ICDE51399.2021.00084 | - |
dc.identifier.hkuros | 339427 | - |
dc.identifier.spage | 912 | - |
dc.identifier.epage | 923 | - |
dc.identifier.isi | WOS:000687830800077 | - |
dc.publisher.place | United States | - |