Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning
Li, Qian, Joty, Shafiq, Wang, Daling, Feng, Shi, Zhang, Yifei
–arXiv.org Artificial Intelligence
Sparsity of formal knowledge and roughness of non-ontological construction make sparsity problem particularly prominent in Open Knowledge Graphs (OpenKGs). Due to sparse links, learning effective representation for few-shot entities becomes difficult. We hypothesize that by introducing negative samples, a contrastive learning (CL) formulation could be beneficial in such scenarios. However, existing CL methods model KG triplets as binary objects of entities ignoring the relation-guided ternary propagation patterns and they are too generic, i.e., they ignore zero-shot, few-shot and synonymity problems that appear in OpenKGs. To address this, we propose TernaryCL, a CL framework based on ternary propagation patterns among head, relation and tail. TernaryCL designs Contrastive Entity and Contrastive Relation to mine ternary discriminative features with both negative entities and relations, introduces Contrastive Self to help zero- and few-shot entities learn discriminative features, Contrastive Synonym to model synonymous entities, and Contrastive Fusion to aggregate graph features from multiple paths. Extensive experiments on benchmarks demonstrate the superiority of TernaryCL over state-of-the-art models.
arXiv.org Artificial Intelligence
Nov-7-2022
- Country:
- North America
- Dominican Republic (0.04)
- United States
- Nevada (0.04)
- Texas (0.04)
- Minnesota > Hennepin County
- Minneapolis (0.14)
- California > San Diego County
- San Diego (0.04)
- Hawaii > Honolulu County
- Honolulu (0.04)
- New York
- New York County > New York City (0.14)
- Richmond County > New York City (0.04)
- Queens County > New York City (0.04)
- Kings County > New York City (0.04)
- Bronx County > New York City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Massachusetts > Hampshire County
- Amherst (0.04)
- Washington > King County
- Seattle (0.04)
- Canada > Quebec
- Capitale-Nationale Region
- Québec (0.04)
- Quebec City (0.04)
- Capitale-Nationale Region
- Europe
- Asia
- Africa > Ethiopia
- Addis Ababa > Addis Ababa (0.04)
- North America
- Genre:
- Research Report (1.00)
- Technology: