Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs

Chen, Mingyang; Zhang, Wen; Zhang, Wei; Chen, Qiang; Chen, Huajun

doi:10.48550/arxiv.1909.01515

Cited by 14 publications

(14 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meta-GNN [48] and Meta-Graph [49] are gradient-base metalearning approaches in few-shot setting for node classification and link prediction. MetaR [50] is a meta relational learning framework to focus on transferring relation-specific meta information in few-shot link prediction. Besides, G-META [51] can learn transferable knowledge faster via meta gradients by leveraging local subgraphs.…”

Section: Meta-learningmentioning

confidence: 99%

Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning

Hwang¹,

Park²,

Kwon³

et al. 2021

Preprint

View full text Add to dashboard Cite

In recent years, graph neural networks (GNNs) have been widely adopted in representation learning of graph-structured data and provided state-of-the-art performance in various application such as link prediction and node classification. Simultaneously, self-supervised learning has been studied to some extent to leverage rich unlabeled data in representation learning on graphs. However, employing self-supervision tasks as auxiliary tasks to assist a primary task has been less explored in the literature on graphs. In this paper, we propose a novel self-supervised auxiliary learning framework to effectively learn graph neural networks. Moreover, we design first a meta-path prediction as a self-supervised auxiliary task for heterogeneous graphs. Our method is learning to learn a primary task with various auxiliary tasks to improve generalization performance. The proposed method identifies an effective combination of auxiliary tasks and automatically balances them to improve the primary task. Our methods can be applied to any graph neural networks in a plug-in manner without manual labeling or additional data. Also, it can be extended to any other auxiliary tasks. Our experiments demonstrate that the proposed method consistently improves the performance of link prediction and node classification on heterogeneous graphs.

show abstract

Section: Meta-learningmentioning

confidence: 99%

Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning

Hwang¹,

Park²,

Kwon³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…For the low resource setting, [44] proposed a one-shot relational learning framework, which learns a matching metric by considering both the learned embeddings and one-hop graph structures. [6] proposed a Meta Relational Learning (MetaR) framework to do few-shot link prediction in KGs. [59] propose a novel framework IterE iteratively learning embeddings and rules which can improve the quality of sparse entity embeddings and their link prediction results.…”

Section: Related Workmentioning

confidence: 99%

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Zhang

Deng

Sun

et al. 2020

Proceedings of the Web Conference 2020

Self Cite

View full text Add to dashboard Cite

Knowledge Graph Completion (KGC) has been proposed to improve Knowledge Graphs by filling in missing connections via link prediction or relation extraction. One of the main difficulties for KGC is a low resource problem. Previous approaches assume sufficient training triples to learn versatile vectors for entities and relations, or a satisfactory number of labeled sentences to train a competent relation extraction model. However, low resource relations are very common in KGs, and those newly added relations often do not have many known samples for training. In this work, we aim at predicting new facts under a challenging setting where only limited training instances are available. We propose a general framework called Weighted Relation Adversarial Network, which utilizes an adversarial procedure to help adapt knowledge/features learned from high resource relations to different but related low resource relations. Specifically, the framework takes advantage of a relation discriminator to distinguish between samples from different relations, and help learn relation-invariant features more transferable from source relations to target relations. Experimental results show that the proposed approach outperforms previous methods regarding low resource settings for both link prediction and relation extraction.

show abstract

“…Nevertheless, these KGE models do not naturally generalize in the few-shot scenario, where only a few edges are available for a rare edge type, which challenges learning the relation embedding. This was addressed in (Chen et al, 2019), where a meta-learning model is proposed to learn the relation embeddings in an inductive fashion. However, this inductive-relation KGE model require a specialized training scheme, can not learn inductive node embeddings, and can not incorporate node features if available.…”

Section: Related Workmentioning

confidence: 99%

Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing

Ioannidis,

Zheng,

Karypis

2020

Preprint

View full text Add to dashboard Cite

Predicting interactions among heterogenous graph structured data has numerous applications such as knowledge graph completion, recommendation systems and drug discovery. Often times, the links to be predicted belong to rare types such as the case in repurposing drugs for novel diseases. This motivates the task of fewshot link prediction. Typically, GCNs are illequipped in learning such rare link types since the relation embedding is not learned in an inductive fashion. This paper proposes an inductive RGCN for learning informative relation embeddings even in the few-shot learning regime. The proposed inductive model significantly outperforms the RGCN and state-of-the-art KGE models in few-shot learning tasks. Furthermore, we apply our method on the drug-repurposing knowledge graph (DRKG) for discovering drugs for Covid-19. We pose the drug discovery task as link prediction and learn embeddings for the biological entities that partake in the DRKG. Our initial results corroborate that several drugs used in clinical trials were identified as possible drug candidates. The method in this paper are implemented using the efficient deep graph learning (DGL) (Wang et al., 2019).

show abstract

Meta Relational Learning for Few-Shot Link Prediction in Knowledge Graphs

Cited by 14 publications

References 16 publications

Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning

Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing

Contact Info

Product

Resources

About