With margin-based losses that allow positive triples to score below a bound rather than exactly zero, TransE can encode symmetric and reflexive relations, and a new complex-space variant TransComplEx gives competitive results.
Improved Knowledge Graph Embedding using Background Taxonomic Information
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Knowledge graphs are used to represent relational information in terms of triples. To enable learning about domains, embedding models, such as tensor factorization models, can be used to make predictions of new triples. Often there is background taxonomic information (in terms of subclasses and subproperties) that should also be taken into account. We show that existing fully expressive (a.k.a. universal) models cannot provably respect subclass and subproperty information. We show that minimal modifications to an existing knowledge graph completion method enables injection of taxonomic information. Moreover, we prove that our model is fully expressive, assuming a lower-bound on the size of the embeddings. Experimental results on public knowledge graphs show that despite its simplicity our approach is surprisingly effective.
fields
cs.AI 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Toward Understanding The Effect Of Loss function On Then Performance Of Knowledge Graph Embedding
With margin-based losses that allow positive triples to score below a bound rather than exactly zero, TransE can encode symmetric and reflexive relations, and a new complex-space variant TransComplEx gives competitive results.