paper-with-me

Papers

InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions

2019-11-01 · Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Nilesh Agrawal, Partha Talukdar

Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas -- feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9%, 7.5%, and 23% better than ConvE on the FB15k-237, WN18RR and YAGO3-10 datasets respectively. The results validate our central hypothesis -- that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research.

📄 PDF Abstract BibTeX arXiv:1911.00219

Code (1)

malllabiisc/InteractE 공식 구현 pytorch

Tasks

Knowledge Graph EmbeddingsKnowledge GraphsLink PredictionPrediction

Similar Papers 제목 키워드 기반

Item Graph Convolution Collaborative Filtering for Inductive Recommendations

2023-03-28 · Edoardo D'Amico, Khalil Muhammad, Elias Tragos, Barry Smyth 외

Graph Convolutional Networks (GCN) have been recently employed as core component in the construction of recommender system algorithms, interpreting user-item interactions as the edges of a bipartite graph. However, in th…

Collaborative FilteringRecommendation Systems

Interest-aware Message-Passing GCN for Recommendation

2021-02-19 · Fan Liu, Zhiyong Cheng, Lei Zhu, Zan Gao 외

Graph Convolution Networks (GCNs) manifest great potential in recommendation. This is attributed to their capability on learning good user and item embeddings by exploiting the collaborative signals from the high-order n…

ComDensE : Combined Dense Embedding of Relation-aware and Common Features for Knowledge Graph Completion

2022-06-29 · Minsang Kim, Seungjun Baek

Real-world knowledge graphs (KG) are mostly incomplete. The problem of recovering missing relations, called KG completion, has recently become an active research area. Knowledge graph (KG) embedding, a low-dimensional re…

Inductive BiasKnowledge Graph CompletionKnowledge GraphsLink Prediction+2

Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks

2018-09-12 · ACL 2019 7 · Shikhar Vashishth, Manik Bhandari, Prateek Yadav, Piyush Rai 외

Word embeddings have been widely adopted across several NLP applications. Most existing word embedding methods utilize sequential context of a word to learn its embedding. While there have been some attempts at utilizing…

Learning Word EmbeddingsRepresentation LearningWord Embeddings

ConvD: Attention Enhanced Dynamic Convolutional Embeddings for Knowledge Graph Completion

2023-12-11 · Wenbin Guo, Zhao Li, Xin Wang, Zirui Chen

Knowledge graphs generally suffer from incompleteness, which can be alleviated by completing the missing information. Deep knowledge convolutional embedding models based on neural networks are currently popular methods f…

Entity EmbeddingsKnowledge Graph CompletionKnowledge GraphsRelation