Digitala Vetenskapliga Arkivet

Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
SchemaWalk: Schema Aware Random Walks for Heterogeneous Graph Embedding
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).ORCID iD: 0000-0002-0223-8907
KTH, School of Electrical Engineering and Computer Science (EECS).ORCID iD: 0000-0001-7898-0879
KTH, School of Electrical Engineering and Computer Science (EECS).ORCID iD: 0000-0003-4516-7317
2022 (English)In: WWW 2022 - Companion Proceedings of the Web Conference 2022, Association for Computing Machinery (ACM) , 2022, p. 1157-1166Conference paper, Published paper (Refereed)
Abstract [en]

Heterogeneous Information Network (HIN) embedding has been a prevalent approach to learn representations off semantically-rich heterogeneous networks. Most HIN embedding methods exploit meta-paths to retain high-order structures, yet, their performance is conditioned on the quality of the (generated/manually-defined) meta-paths and their suitability for the specific label set. Whereas other methods adjust random walks to harness or skip certain heterogeneous structures (e.g. node type(s)), in doing so, the adjusted random walker may casually omit other node/edge types. Our key insight is with no domain knowledge, the random walker should hold no assumptions about heterogeneous structure (i.e. edge types). Thus, aiming for a flexible and general method, we utilize network schema as a unique blueprint of HIN, and propose SchemaWalk, a random walk to uniformly sample all edge types within the network schema. Moreover, we identify the starvation phenomenon which induces random walkers on HINs to under- or over-sample certain edge types. Accordingly, we design SchemaWalkHO to skip local deficient connectivity to preserve uniform sampling distribution. Finally, we carry out node classification experiments on four real-world HINs, and provide in-depth qualitative analysis. The results highlight the robustness of our method regardless to the graph structure in contrast with the state-of-the-art baselines. 

Place, publisher, year, edition, pages
Association for Computing Machinery (ACM) , 2022. p. 1157-1166
Keywords [en]
Heterogeneous Information Network, Network Embeddings, Random Walk, Representation Learning, Domain Knowledge, Graphic methods, Information services, Random processes, Graph embeddings, Heterogeneous graph, Heterogeneous information, Heterogeneous structures, Information networks, Network embedding, Random walkers, Heterogeneous networks
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:kth:diva-327049DOI: 10.1145/3487553.3524728Scopus ID: 2-s2.0-85137448476OAI: oai:DiVA.org:kth-327049DiVA, id: diva2:1758490
Conference
31st ACM Web Conference, WWW 2022, 25 April 2022
Note

QC 20230523

Available from: 2023-05-23 Created: 2023-05-23 Last updated: 2023-05-23Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Samy, AhmedGiaretta, LodovicoKefato, Zekarias TilahunGirdzijauskas, Sarunas
By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 32 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf