One-Shot Relational Learning for Knowledge Graphs

Xiong, Wenhan; Yu, Mo; Chang, Shiyu; Guo, Xiaoxiao; Wang, William Yang

doi:10.18653/v1/d18-1223

Cited by 183 publications

(171 citation statements)

References 38 publications

Supporting

Mentioning

160

Contrasting

Order By: Relevance

“…To do few-shot link prediction, Xiong et al (2018) made the first trial and proposed GMatching, learning a matching metric by considering both learned embeddings and one-hop graph structures, while we try to accomplish few-shot link prediction from another perspective based on the intuition that the most important information to be transferred from a few existing instances to incomplete triples should be the common and shared knowledge within one task. We call such information relation-specific meta information and propose a new framework Meta Relational Learning (MetaR) for few-shot link prediction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Chen¹,

Zhang²,

Zhang³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

156

114

View full text Add to dashboard Cite

Link prediction is an important way to complete knowledge graphs (KGs), while embedding-based methods, effective for link prediction in KGs, perform poorly on relations that only have a few associative triples. In this work, we propose a Meta Relational Learning (MetaR) framework to do the common but challenging few-shot link prediction in KGs, namely predicting new triples about a relation by only observing a few associative triples. We solve few-shot link prediction by focusing on transferring relation-specific meta information to make model learn the most important knowledge and learn faster, corresponding to relation meta and gradient meta respectively in MetaR. Empirically, our model achieves stateof-the-art results on few-shot link prediction KG benchmarks.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Compared with GMatching (Xiong et al, 2018) which relies on a background knowledge graph, our MetaR is independent with them, thus is more robust as background knowledge graphs might not be available for few-shot link prediction in real scenarios.…”

Section: Introductionmentioning

confidence: 99%

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

Chen¹,

Zhang²,

Zhang³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

156

114

View full text Add to dashboard Cite

show abstract

“…KG-BERT [46] takes entity and relation descriptions of a triple as input and computes scoring function of the triple with BERT. 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.…”

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

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

“…In this paper, we test Graph Convolution Network (GCN) and Onto2vec. There are other node embedding methods, but GCN has shown to work well in practice for prediction tasks when labels have low occurrence frequencies [9,19,27].…”

Section: Entity Encodersmentioning

confidence: 99%

“…For example, distance metric for GO terms can be inferred from the GO tree or their definitions, and then be used as the intuitive constraint that forces similar terms to have equivalent prediction probabilities for a given protein sequence [24]. More importantly, for rare label prediction problems, works in other research domains have shown that using vector representations of labels as one of the features can boost the classification accuracy [2,19,27]. This paper will focus on the second data resource, the Gene Ontology itself.…”

Section: Introductionmentioning

confidence: 99%

Evaluating Representations for Gene Ontology Terms

Duong

Uppunda

et al. 2019

Preprint

View full text Add to dashboard Cite

Functions of proteins are annotated by Gene Ontology (GO) terms. As the amount of new sequences being collected is rising at a faster pace than the number of sequences being annotated with GO terms, there have been efforts to develop better annotation techniques. When annotating protein sequences with GO terms, one key auxiliary resource is the GO data itself. GO terms have definitions consisted of a few sentences describing some biological events, and are also arranged in a tree structure with specific terms being child nodes of generic terms. The definitions and positions of the GO terms on the GO tree can be used to construct vector representations for the GO terms. These GO vectors can then be integrated into existing prediction models to improve the classification accuracy. In this paper, we adapt the Bidirectional Encoder Representations from Transformers (BERT) to encode GO definitions into vectors. We evaluate BERT against the previous GO encoders in three tasks: (1) measuring similarity between GO terms (2) asserting relationship for orthologs and interacting proteins based on their GO annotations and (3) predicting GO terms for protein sequences. For task 3, we show that using GO vectors as additional prediction features increases the accuracy, primarily for GO terms with low occurrences in the manually annotated dataset. In all three tasks, BERT often outperforms the previous GO encoders.https://www.uniprot.org/

show abstract

One-Shot Relational Learning for Knowledge Graphs

Cited by 183 publications

References 38 publications

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

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

Relation Adversarial Network for Low Resource Knowledge Graph Completion

Evaluating Representations for Gene Ontology Terms

Contact Info

Product

Resources

About