Abstract
The main focus of relational learning for knowledge graph completion (KGC) lies in exploiting rich contextual information for facts. Many state-of-the-art models incorporate fact sequences, entity types, and even textual information. Unfortunately, most of them do not fully take advantage of rich structural information in a KG, i.e., connectivity patterns around each entity. In this paper, we propose a context-aware convolutional learning (CACL) model which jointly learns from entities and their multi-hop neighborhoods. Since we directly utilize the connectivity patterns contained in each multi-hop neighborhood, the structural role similarity among entities can be better captured, resulting in more informative entity and relation embeddings. Specifically, CACL collects entities and relations from the multi-hop neighborhood as contextual information according to their relative importance and uniquely maps them to a linear vector space. Our convolutional architecture leverages a deep learning technique to represent each entity along with its linearly mapped contextual information. Thus, we can elaborately extract the features of key connectivity patterns from the context and incorporate them into a score function which evaluates the validity of facts. Experimental results on the newest datasets show that CACL outperforms existing approaches by successfully enriching embeddings with neighborhood information.
| Original language | English |
|---|---|
| Title of host publication | CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management |
| Editors | Norman Paton, Selcuk Candan, Haixun Wang, James Allan, Rakesh Agrawal, Alexandros Labrinidis, Alfredo Cuzzocrea, Mohammed Zaki, Divesh Srivastava, Andrei Broder, Assaf Schuster |
| Publisher | Association for Computing Machinery |
| Pages | 257-266 |
| Number of pages | 10 |
| ISBN (Electronic) | 9781450360142 |
| DOIs | |
| Publication status | Published - 2018 Oct 17 |
| Event | 27th ACM International Conference on Information and Knowledge Management, CIKM 2018 - Torino, Italy Duration: 2018 Oct 22 → 2018 Oct 26 |
Publication series
| Name | International Conference on Information and Knowledge Management, Proceedings |
|---|
Other
| Other | 27th ACM International Conference on Information and Knowledge Management, CIKM 2018 |
|---|---|
| Country | Italy |
| City | Torino |
| Period | 18/10/22 → 18/10/26 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Business, Management and Accounting(all)
- Decision Sciences(all)
Cite this
}
Knowledge graph completion by context-aware convolutional learning with multi-hop neighborhoods. / Oh, Byungkook; Seo, Seungmin; Lee, Kyong Ho.
CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management. ed. / Norman Paton; Selcuk Candan; Haixun Wang; James Allan; Rakesh Agrawal; Alexandros Labrinidis; Alfredo Cuzzocrea; Mohammed Zaki; Divesh Srivastava; Andrei Broder; Assaf Schuster. Association for Computing Machinery, 2018. p. 257-266 (International Conference on Information and Knowledge Management, Proceedings).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - Knowledge graph completion by context-aware convolutional learning with multi-hop neighborhoods
AU - Oh, Byungkook
AU - Seo, Seungmin
AU - Lee, Kyong Ho
PY - 2018/10/17
Y1 - 2018/10/17
N2 - The main focus of relational learning for knowledge graph completion (KGC) lies in exploiting rich contextual information for facts. Many state-of-the-art models incorporate fact sequences, entity types, and even textual information. Unfortunately, most of them do not fully take advantage of rich structural information in a KG, i.e., connectivity patterns around each entity. In this paper, we propose a context-aware convolutional learning (CACL) model which jointly learns from entities and their multi-hop neighborhoods. Since we directly utilize the connectivity patterns contained in each multi-hop neighborhood, the structural role similarity among entities can be better captured, resulting in more informative entity and relation embeddings. Specifically, CACL collects entities and relations from the multi-hop neighborhood as contextual information according to their relative importance and uniquely maps them to a linear vector space. Our convolutional architecture leverages a deep learning technique to represent each entity along with its linearly mapped contextual information. Thus, we can elaborately extract the features of key connectivity patterns from the context and incorporate them into a score function which evaluates the validity of facts. Experimental results on the newest datasets show that CACL outperforms existing approaches by successfully enriching embeddings with neighborhood information.
AB - The main focus of relational learning for knowledge graph completion (KGC) lies in exploiting rich contextual information for facts. Many state-of-the-art models incorporate fact sequences, entity types, and even textual information. Unfortunately, most of them do not fully take advantage of rich structural information in a KG, i.e., connectivity patterns around each entity. In this paper, we propose a context-aware convolutional learning (CACL) model which jointly learns from entities and their multi-hop neighborhoods. Since we directly utilize the connectivity patterns contained in each multi-hop neighborhood, the structural role similarity among entities can be better captured, resulting in more informative entity and relation embeddings. Specifically, CACL collects entities and relations from the multi-hop neighborhood as contextual information according to their relative importance and uniquely maps them to a linear vector space. Our convolutional architecture leverages a deep learning technique to represent each entity along with its linearly mapped contextual information. Thus, we can elaborately extract the features of key connectivity patterns from the context and incorporate them into a score function which evaluates the validity of facts. Experimental results on the newest datasets show that CACL outperforms existing approaches by successfully enriching embeddings with neighborhood information.
UR - http://www.scopus.com/inward/record.url?scp=85058008757&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058008757&partnerID=8YFLogxK
U2 - 10.1145/3269206.3271769
DO - 10.1145/3269206.3271769
M3 - Conference contribution
AN - SCOPUS:85058008757
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 257
EP - 266
BT - CIKM 2018 - Proceedings of the 27th ACM International Conference on Information and Knowledge Management
A2 - Paton, Norman
A2 - Candan, Selcuk
A2 - Wang, Haixun
A2 - Allan, James
A2 - Agrawal, Rakesh
A2 - Labrinidis, Alexandros
A2 - Cuzzocrea, Alfredo
A2 - Zaki, Mohammed
A2 - Srivastava, Divesh
A2 - Broder, Andrei
A2 - Schuster, Assaf
PB - Association for Computing Machinery
ER -