-
Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs
Link prediction is an important way to complete knowledge graphs (KGs), ...
read it
-
Conditional Link Prediction of Category-Implicit Keypoint Detection
Keypoints of objects reflect their concise abstractions, while the corre...
read it
-
Adversarial Sets for Regularising Neural Link Predictors
In adversarial training, a set of models learn together by pursuing comp...
read it
-
DRUM: End-To-End Differentiable Rule Mining On Knowledge Graphs
In this paper, we study the problem of learning probabilistic logical ru...
read it
-
Semantic Triple Encoder for Fast Open-Set Link Prediction
We improve both the open-set generalization and efficiency of link predi...
read it
-
Predicting Semantic Relations using Global Graph Properties
Semantic graphs, such as WordNet, are resources which curate natural lan...
read it
-
MLMLM: Link Prediction with Mean Likelihood Masked Language Model
Knowledge Bases (KBs) are easy to query, verifiable, and interpretable. ...
read it
Generalized Relation Learning with Semantic Correlation Awareness for Link Prediction
Developing link prediction models to automatically complete knowledge graphs has recently been the focus of significant research interest. The current methods for the link prediction taskhavetwonaturalproblems:1)the relation distributions in KGs are usually unbalanced, and 2) there are many unseen relations that occur in practical situations. These two problems limit the training effectiveness and practical applications of the existing link prediction models. We advocate a holistic understanding of KGs and we propose in this work a unified Generalized Relation Learning framework GRL to address the above two problems, which can be plugged into existing link prediction models. GRL conducts a generalized relation learning, which is aware of semantic correlations between relations that serve as a bridge to connect semantically similar relations. After training with GRL, the closeness of semantically similar relations in vector space and the discrimination of dissimilar relations are improved. We perform comprehensive experiments on six benchmarks to demonstrate the superior capability of GRL in the link prediction task. In particular, GRL is found to enhance the existing link prediction models making them insensitive to unbalanced relation distributions and capable of learning unseen relations.
READ FULL TEXT
Comments
There are no comments yet.