Relation-dependent Contrastive Learning with Cluster Sampling for Inductive Relation Prediction
Relation prediction is a task designed for knowledge graph completion which aims to predict missing relationships between entities. Recent subgraph-based models for inductive relation prediction have received increasing attention, which can predict relation for unseen entities based on the extracted subgraph surrounding the candidate triplet. However, they are not completely inductive because of their disability of predicting unseen relations. Moreover, they fail to pay sufficient attention to the role of relation as they only depend on the model to learn parameterized relation embedding, which leads to inaccurate prediction on long-tail relations. In this paper, we introduce Relation-dependent Contrastive Learning (ReCoLe) for inductive relation prediction, which adapts contrastive learning with a novel sampling method based on clustering algorithm to enhance the role of relation and improve the generalization ability to unseen relations. Instead of directly learning embedding for relations, ReCoLe allocates a pre-trained GNN-based encoder to each relation to strengthen the influence of relation. The GNN-based encoder is optimized by contrastive learning, which ensures satisfactory performance on long-tail relations. In addition, the cluster sampling method equips ReCoLe with the ability to handle both unseen relations and entities. Experimental results suggest that ReCoLe outperforms state-of-the-art methods on commonly used inductive datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningInductive Relation PredictionKnowledge Graph CompletionPredictionRelationRelation PredictionTripletMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning First-Order Rules with Relational Path Contrast for Inductive Relation Reasoning
Relation reasoning in knowledge graphs (KGs) aims at predicting missing relations in incomplete triples, whereas the dominant paradigm is learning the embeddings of relations and entities, which is limited to a transduct…
Knowledge GraphsRelationHow does Contrastive Learning Organize Images?
Contrastive learning, a dominant self-supervised technique, emphasizes similarity in representations between augmentations of the same input and dissimilarity for different ones. Although low contrastive loss often corre…
ClusteringContrastive LearningThe Loss Is Not Enough: Sampling Conditions and Inductive Bias in Contrastive Representation Learning
Contrastive learning has become a leading paradigm for self-supervised representation learning, yet the conditions under which it recovers meaningful latent geometry remain incompletely understood. We develop a measure-t…
Representation LearningContrastive LearningFailure-Proof Non-Contrastive Self-Supervised Learning
We identify sufficient conditions to avoid known failure modes, including representation, dimensional, cluster and intracluster collapses, occurring in non-contrastive self-supervised learning. Based on these findings, w…
Inductive BiasSelf-Supervised LearningA Contrastive Variational Graph Auto-Encoder for Node Clustering
Variational Graph Auto-Encoders (VGAEs) have been widely used to solve the node clustering task. However, the state-of-the-art methods have numerous challenges. First, existing VGAEs do not account for the discrepancy be…
ClusteringContrastive LearningInductive BiasNode Clustering