In this paper, the concepts of falling fuzzy(implicative, associative) filters of lattice implication algebras based on the theory of falling shadows and fuzzy sets are presented at first. And then the relations betwe...In this paper, the concepts of falling fuzzy(implicative, associative) filters of lattice implication algebras based on the theory of falling shadows and fuzzy sets are presented at first. And then the relations between fuzzy(implicative, associative) filters and falling fuzzy(implicative, associative) filters are provided. In particular, we put forward an open question on a kind of falling fuzzy filters of lattice implication algebras. Finally, we apply falling fuzzy inference relations to lattice implication algebras and obtain some related results.展开更多
Link prediction is used to complete the knowledge graph.Convolu-tional neural network models are commonly used for link prediction tasks,but they only consider the direct relations between entity pairs,ignoring the se...Link prediction is used to complete the knowledge graph.Convolu-tional neural network models are commonly used for link prediction tasks,but they only consider the direct relations between entity pairs,ignoring the semantic information contained in the relation paths.In addition,the embedding dimension of the relation is generally larger than that of the entity in the ConvR model,which blocks the progress of downstream tasks.If we reduce the embedding dimension of the relation,the performance will be greatly degraded.This paper proposes a convolutional model PITri-R-ConvR based on triangular structure relational infer-ence.The model uses relational path inference to capture semantic information,while using a triangular structure to ensure the reliability and computational effi-ciency of relational inference.In addition,the decoder R-ConvR improves the initial embedding of the ConvR model,which solves the problems of the ConvR model and significantly improves the prediction performance.Finally,this paper conducts sufficient experiments in multiple datasets to verify the superiority of the model and the rationality of each module.展开更多
Knowledge graphs(KGs)often suffer from incompleteness,which limits their performance in practice where a vast amount of entities may coexist.To aid,knowledge graph completion(KGC)has been proposed to infer the missing...Knowledge graphs(KGs)often suffer from incompleteness,which limits their performance in practice where a vast amount of entities may coexist.To aid,knowledge graph completion(KGC)has been proposed to infer the missing links between entities.Among them,reasoning over relation paths in incomplete KG is a popular research topic.However,there are still some issues remained to be solved,such as path noise,path sparsity of KG,the ambiguity of inferred relation and lack of explanability in path representation.To simultaneously address the aforementioned challenges,we propose a novel rule guided link prediction model with path noise avoidance and disambiguation of inferred relation,termed as RPND.Specifically,we utilize path selection strategy to filter noisy path and reduce the interference of path noise.To alleviate the path sparsity of KG,we leverage path overlapping feature of similar relations and combine them based on the semantic similarity.For the ambiguity of inferred relation,we draw the insight from language model like transformer by introducing position embedding to reflect the order of relation along the path when learning its representation.Meanwhile,we employ logic rules to compose paths in semantic level to enhance the explanability of path representation.Extensive experiments conducted on benchmark datasets demonstrate the superiority of our proposed RPND model compared to its SOTAs.展开更多
基金Supported by National Natural Science Foundation of China(11461025,61175055)
文摘In this paper, the concepts of falling fuzzy(implicative, associative) filters of lattice implication algebras based on the theory of falling shadows and fuzzy sets are presented at first. And then the relations between fuzzy(implicative, associative) filters and falling fuzzy(implicative, associative) filters are provided. In particular, we put forward an open question on a kind of falling fuzzy filters of lattice implication algebras. Finally, we apply falling fuzzy inference relations to lattice implication algebras and obtain some related results.
基金This work was supported by the National Key R&D Program of China under Grant No.20201710200.
文摘Link prediction is used to complete the knowledge graph.Convolu-tional neural network models are commonly used for link prediction tasks,but they only consider the direct relations between entity pairs,ignoring the semantic information contained in the relation paths.In addition,the embedding dimension of the relation is generally larger than that of the entity in the ConvR model,which blocks the progress of downstream tasks.If we reduce the embedding dimension of the relation,the performance will be greatly degraded.This paper proposes a convolutional model PITri-R-ConvR based on triangular structure relational infer-ence.The model uses relational path inference to capture semantic information,while using a triangular structure to ensure the reliability and computational effi-ciency of relational inference.In addition,the decoder R-ConvR improves the initial embedding of the ConvR model,which solves the problems of the ConvR model and significantly improves the prediction performance.Finally,this paper conducts sufficient experiments in multiple datasets to verify the superiority of the model and the rationality of each module.
基金supported in part by the National Natural Science Foundation of China(Grant Nos.62120106008,62376085).
文摘Knowledge graphs(KGs)often suffer from incompleteness,which limits their performance in practice where a vast amount of entities may coexist.To aid,knowledge graph completion(KGC)has been proposed to infer the missing links between entities.Among them,reasoning over relation paths in incomplete KG is a popular research topic.However,there are still some issues remained to be solved,such as path noise,path sparsity of KG,the ambiguity of inferred relation and lack of explanability in path representation.To simultaneously address the aforementioned challenges,we propose a novel rule guided link prediction model with path noise avoidance and disambiguation of inferred relation,termed as RPND.Specifically,we utilize path selection strategy to filter noisy path and reduce the interference of path noise.To alleviate the path sparsity of KG,we leverage path overlapping feature of similar relations and combine them based on the semantic similarity.For the ambiguity of inferred relation,we draw the insight from language model like transformer by introducing position embedding to reflect the order of relation along the path when learning its representation.Meanwhile,we employ logic rules to compose paths in semantic level to enhance the explanability of path representation.Extensive experiments conducted on benchmark datasets demonstrate the superiority of our proposed RPND model compared to its SOTAs.
