Abstract | ||
---|---|---|
Lacking in sequence preserving mechanism, existing heterogeneous information network (HIN) embedding discards the essential type sequence information during embedding. We propose a Type Sequence Preserving HIN Embedding model (SeqHINE) which expands the HIN embedding to sequence level. SeqHINE incorporates the type sequence information via type-aware GRU and preserves representative sequence information by decay function. Abundant experiments show that SeqHINE can outperform state-of-the-art even with 50% less labeled data. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1609/aaai.v33i01.33019931 | AAAI |
Field | DocType | Volume |
Embedding,Computer science,Theoretical computer science,Artificial intelligence,Network embedding,Labeled data,Machine learning | Conference | 33 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuxin Chen | 1 | 3 | 1.73 |
WANG Teng-Jiao | 2 | 352 | 48.09 |
Wei Chen | 3 | 0 | 0.34 |
Qiang Li | 4 | 599 | 54.40 |
Zhen Qiu | 5 | 0 | 0.34 |