SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

Xiao, Han; Huang, Minlie; Lian, Meng; Zhu, Xiaoyan

doi:10.1609/aaai.v31i1.10952

Cited by 81 publications

(23 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge Graph Representation Learning Representation learning has shown great success in a wide range of fields (Zhang et al , 2017Li et al 2021;Yuan et al 2021) and KG reasoning is no exception. Recent advances in this area have proposed a variety of embeddingbased methods that project the entities and relations into low-dimensional continuous vector space by exploiting entity types (Guo et al 2015;Ouyang et al 2017), relation paths (Lin et al 2015a;Toutanova et al 2016;Li et al 2018a;Zhang et al 2018), textual descriptions (Zhong et al 2015;Xiao et al 2017), and logical rules (Omran, Wang, and Wang 2018;Hamilton et al 2018). For instance, TransE (Wang et al 2014) first encoded the entities and relations into latent vectors by following translational principle in point-wise Euclidean space.…”

Section: Related Workmentioning

confidence: 99%

Learning to Walk with Dual Agents for Knowledge Graph Reasoning

Zhang

Yuan

Líu³

et al. 2022

AAAI

View full text Add to dashboard Cite

Graph walking based on reinforcement learning (RL) has shown great success in navigating an agent to automatically complete various reasoning tasks over an incomplete knowledge graph (KG) by exploring multi-hop relational paths. However, existing multi-hop reasoning approaches only work well on short reasoning paths and tend to miss the target entity with the increasing path length. This is undesirable for many reasoning tasks in real-world scenarios, where short paths connecting the source and target entities are not available in incomplete KGs, and thus the reasoning performances drop drastically unless the agent is able to seek out more clues from longer paths. To address the above challenge, in this paper, we propose a dual-agent reinforcement learning framework, which trains two agents (Giant and Dwarf) to walk over a KG jointly and search for the answer collaboratively. Our approach tackles the reasoning challenge in long paths by assigning one of the agents (Giant) searching on cluster-level paths quickly and providing stage-wise hints for another agent (Dwarf). Finally, experimental results on several KG reasoning benchmarks show that our approach can search answers more accurately and efficiently, and outperforms existing RL-based methods for long path queries by a large margin.

show abstract

Section: Related Workmentioning

confidence: 99%

Learning to Walk with Dual Agents for Knowledge Graph Reasoning

Zhang

Yuan

Líu³

et al. 2022

AAAI

View full text Add to dashboard Cite

show abstract

“…Even though there are a large number of successful researches in modeling relational facts, most of them can only train an embedding model on an observed triplets dataset. Thereupon, there are increasing studies that focus on learning more generalizing KG embedding models by absorbing additional information, such as entity types [28,29], relation paths [30][31][32], and textual descriptions [33][34][35].…”

Section: Elon Musk Founderof Locatedinmentioning

confidence: 99%

A Survey on Knowledge Graph Embedding: Approaches, Applications and Benchmarks

et al. 2020

View full text Add to dashboard Cite

A knowledge graph (KG), also known as a knowledge base, is a particular kind of network structure in which the node indicates entity and the edge represent relation. However, with the explosion of network volume, the problem of data sparsity that causes large-scale KG systems to calculate and manage difficultly has become more significant. For alleviating the issue, knowledge graph embedding is proposed to embed entities and relations in a KG to a low-, dense and continuous feature space, and endow the yield model with abilities of knowledge inference and fusion. In recent years, many researchers have poured much attention in this approach, and we will systematically introduce the existing state-of-the-art approaches and a variety of applications that benefit from these methods in this paper. In addition, we discuss future prospects for the development of techniques and application trends. Specifically, we first introduce the embedding models that only leverage the information of observed triplets in the KG. We illustrate the overall framework and specific idea and compare the advantages and disadvantages of such approaches. Next, we introduce the advanced models that utilize additional semantic information to improve the performance of the original methods. We divide the additional information into two categories, including textual descriptions and relation paths. The extension approaches in each category are described, following the same classification criteria as those defined for the triplet fact-based models. We then describe two experiments for comparing the performance of listed methods and mention some broader domain tasks such as question answering, recommender systems, and so forth. Finally, we collect several hurdles that need to be overcome and provide a few future research directions for knowledge graph embedding.

show abstract

“…Most of the currently available techniques perform the embedding task based solely on triples observed in a KG. Some recent work further tried to use other information, e.g., entity types (Guo et al 2015; and textual descriptions Xiao, Huang, and Zhu 2017), to learn more predictive embeddings. See (Wang et al 2017) for a thorough review of KG embedding techniques.…”

Section: Related Workmentioning

confidence: 99%

Knowledge Graph Embedding With Iterative Guidance From Soft Rules

Guo

Wang

et al. 2018

AAAI

136

View full text Add to dashboard Cite

Embedding knowledge graphs (KGs) into continuous vector spaces is a focus of current research. Combining such an embedding model with logic rules has recently attracted increasing attention. Most previous attempts made a one-time injection of logic rules, ignoring the interactive nature between embedding learning and logical inference. And they focused only on hard rules, which always hold with no exception and usually require extensive manual effort to create or validate. In this paper, we propose Rule-Guided Embedding (RUGE), a novel paradigm of KG embedding with iterative guidance from soft rules. RUGE enables an embedding model to learn simultaneously from 1) labeled triples that have been directly observed in a given KG, 2) unlabeled triples whose labels are going to be predicted iteratively, and 3) soft rules with various confidence levels extracted automatically from the KG. In the learning process, RUGE iteratively queries rules to obtain soft labels for unlabeled triples, and integrates such newly labeled triples to update the embedding model. Through this iterative procedure, knowledge embodied in logic rules may be better transferred into the learned embeddings. We evaluate RUGE in link prediction on Freebase and YAGO. Experimental results show that: 1) with rule knowledge injected iteratively, RUGE achieves significant and consistent improvements over state-of-the-art baselines; and 2) despite their uncertainties, automatically extracted soft rules are highly beneficial to KG embedding, even those with moderate confidence levels. The code and data used for this paper can be obtained from https://github.com/iieir-km/RUGE.

show abstract

SSP: Semantic Space Projection for Knowledge Graph Embedding with Text Descriptions

Cited by 81 publications

References 16 publications

Learning to Walk with Dual Agents for Knowledge Graph Reasoning

Learning to Walk with Dual Agents for Knowledge Graph Reasoning

A Survey on Knowledge Graph Embedding: Approaches, Applications and Benchmarks

Knowledge Graph Embedding With Iterative Guidance From Soft Rules

Contact Info

Product

Resources

About