# Relation Adversarial Network for Low Resource Knowledge Graph Completion

arXiv: https://arxiv.org/abs/1911.03091 · HTML: https://mlsanity.com/paper/1911.03091/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2019.

## Built on by (most cited first, 24 of 24)

- [Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2108.13161/) (2021)
- [Document-level Relation Extraction as Semantic Segmentation](https://mlsanity.com/paper/2106.03618/) (2021)
- [From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer](https://mlsanity.com/paper/2202.02113/) (2022)
- [AliCG: Fine-grained and Evolvable Conceptual Graph Construction for Semantic Search at Alibaba](https://mlsanity.com/paper/2106.01686/) (2021)
- [Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding](https://mlsanity.com/paper/2110.14170/) (2021)
- [Eider: Empowering Document-level Relation Extraction with Efficient Evidence Extraction and Inference-stage Fusion](https://mlsanity.com/paper/2106.08657/) (2021)
- [Ontology-enhanced Prompt-tuning for Few-shot Learning](https://mlsanity.com/paper/2201.11332/) (2022)
- [Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2112.10006/) (2021)
- [Editing Language Model-based Knowledge Graph Embeddings](https://mlsanity.com/paper/2301.10405/) (2023)
- [DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population](https://mlsanity.com/paper/2201.03335/) (2022)
- [Reasoning Through Memorization: Nearest Neighbor Knowledge Graph Embeddings](https://mlsanity.com/paper/2201.05575/) (2022)
- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Information Extraction in Low-Resource Scenarios: Survey and Perspective](https://mlsanity.com/paper/2202.08063/) (2022)
- [A Survey On Few-shot Knowledge Graph Completion with Structural and Commonsense Knowledge](https://mlsanity.com/paper/2301.01172/) (2023)
- [LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training](https://mlsanity.com/paper/2112.01404/) (2021)
- [Normal vs. Adversarial: Salience-based Analysis of Adversarial Samples for Relation Extraction](https://mlsanity.com/paper/2104.00312/) (2021)
- [Schema-adaptable Knowledge Graph Construction](https://mlsanity.com/paper/2305.08703/) (2023)
- [Text-guided Legal Knowledge Graph Reasoning](https://mlsanity.com/paper/2104.02284/) (2021)
- [ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning](https://mlsanity.com/paper/2102.12828/) (2021)
- [Speaker-Oriented Latent Structures for Dialogue-Based Relation Extraction](https://mlsanity.com/paper/2109.05182/) (2021)
- [A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction](https://mlsanity.com/paper/2203.13953/) (2022)
- [NC-DRE: Leveraging Non-entity Clue Information for Document-level Relation Extraction](https://mlsanity.com/paper/2204.00255/) (2022)
- [A Pre-training Framework for Knowledge Graph Completion](https://mlsanity.com/paper/2302.02614/) (2023)
- [READ: Improving Relation Extraction from an ADversarial Perspective](https://mlsanity.com/paper/2404.02931/) (2024)

## Abstract (arXiv)

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.