Link-Intensive Alignment for Incomplete Knowledge Graphs

• URL: http://arxiv.org/abs/2112.09266v1
• Date: Fri, 17 Dec 2021 00:41:28 GMT
• Title: Link-Intensive Alignment for Incomplete Knowledge Graphs
• Authors: Vinh Van Tong, Thanh Trung Huynh, Thanh Tam Nguyen, Hongzhi Yin, Quoc Viet Hung Nguyen and Quyet Thang Huynh
• Abstract summary: In this work, we address the problem of aligning incomplete KGs with representation learning. Our framework exploits two feature channels: transitivity-based and proximity-based. The two feature channels are jointly learned to exchange important features between the input KGs. Also, we develop a missing links detector that discovers and recovers the missing links during the training process.
• Score: 28.213397255810936
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge graph (KG) alignment - the task of recognizing entities referring to the same thing in different KGs - is recognized as one of the most important operations in the field of KG construction and completion. However, existing alignment techniques often assume that the input KGs are complete and isomorphic, which is not true due to the real-world heterogeneity in the domain, size, and sparsity. In this work, we address the problem of aligning incomplete KGs with representation learning. Our KG embedding framework exploits two feature channels: transitivity-based and proximity-based. The former captures the consistency constraints between entities via translation paths, while the latter captures the neighbourhood structure of KGs via attention guided relation-aware graph neural network. The two feature channels are jointly learned to exchange important features between the input KGs while enforcing the output representations of the input KGs in the same embedding space. Also, we develop a missing links detector that discovers and recovers the missing links in the input KGs during the training process, which helps mitigate the incompleteness issue and thus improve the compatibility of the learned representations. The embeddings then are fused to generate the alignment result, and the high-confidence matched node pairs are updated to the pre-aligned supervision data to improve the embeddings gradually. Empirical results show that our model is up to 15.2\% more accurate than the SOTA and is robust against different levels of incompleteness. We also demonstrate that the knowledge exchanging between the KGs helps reveal the unseen facts from knowledge graphs (a.k.a. knowledge completion), with the result being 3.5\% higher than the SOTA knowledge graph completion techniques.

Related papers

• EntailE: Introducing Textual Entailment in Commonsense Knowledge Graph Completion [54.12709176438264]
  Commonsense knowledge graphs (CSKGs) utilize free-form text to represent named entities, short phrases, and events as their nodes. Current methods leverage semantic similarities to increase the graph density, but the semantic plausibility of the nodes and their relations are under-explored. We propose to adopt textual entailment to find implicit entailment relations between CSKG nodes, to effectively densify the subgraph connecting nodes within the same conceptual class.
  arXiv  Detail & Related papers  (2024-02-15T02:27:23Z)
• On the Sweet Spot of Contrastive Views for Knowledge-enhanced Recommendation [49.18304766331156]
  We propose a new contrastive learning framework for KG-enhanced recommendation. We construct two separate contrastive views for KG and IG, and maximize their mutual information. Extensive experimental results on three real-world datasets demonstrate the effectiveness and efficiency of our method.
  arXiv  Detail & Related papers  (2023-09-23T14:05:55Z)
• i-Align: an interpretable knowledge graph alignment model [35.13345855672941]
  Knowledge graphs (KGs) are becoming essential resources for many downstream applications. One of the strategies to address this problem is KG alignment, forming a more complete KG by merging two or more KGs. This paper proposes i-Align, an interpretable KG alignment model.
  arXiv  Detail & Related papers  (2023-08-26T03:48:52Z)
• Collective Knowledge Graph Completion with Mutual Knowledge Distillation [11.922522192224145]
  We study the problem of multi-KG completion, where we focus on maximizing the collective knowledge from different KGs. We propose a novel method called CKGC-CKD that uses relation-aware graph convolutional network encoder models on both individual KGs and a large fused KG. Experimental results on multilingual datasets have shown that our method outperforms all state-of-the-art models in the KGC task.
  arXiv  Detail & Related papers  (2023-05-25T09:49:40Z)
• Pre-training Transformers for Knowledge Graph Completion [81.4078733132239]
  We introduce a novel inductive KG representation model (iHT) for learning transferable representation for knowledge graphs. iHT consists of a entity encoder (e.g., BERT) and a neighbor-aware relational scoring function both parameterized by Transformers. Our approach achieves new state-of-the-art results on matched evaluations, with a relative improvement of more than 25% in mean reciprocal rank over previous SOTA models.
  arXiv  Detail & Related papers  (2023-03-28T02:10:37Z)
• Mitigating Relational Bias on Knowledge Graphs [51.346018842327865]
  We propose Fair-KGNN, a framework that simultaneously alleviates multi-hop bias and preserves the proximity information of entity-to-relation in knowledge graphs. We develop two instances of Fair-KGNN incorporating with two state-of-the-art KGNN models, RGCN and CompGCN, to mitigate gender-occupation and nationality-salary bias.
  arXiv  Detail & Related papers  (2022-11-26T05:55:34Z)
• Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network [111.67744771462873]
  This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs) It combines high-order reasoning into a graph convolutional network, namely HoGRN. It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
  arXiv  Detail & Related papers  (2022-07-14T10:16:56Z)
• KGNN: Distributed Framework for Graph Neural Knowledge Representation [38.080926752998586]
  We develop a novel framework called KGNN to take full advantage of knowledge data for representation learning in the distributed learning system. KGNN is equipped with GNN based encoder and knowledge aware decoder, which aim to jointly explore high-order structure and attribute information together.
  arXiv  Detail & Related papers  (2022-05-17T12:32:02Z)
• Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment [69.41986652911143]
  We propose a novel self-supervised adaptive graph alignment (SS-AGA) method to predict missing facts in a knowledge graph (KG) SS-AGA fuses all KGs as a whole graph by regarding alignment as a new edge type. Experiments on the public multilingual DBPedia KG and newly-created industrial multilingual E-commerce KG empirically demonstrate the effectiveness of SS-AGA.
  arXiv  Detail & Related papers  (2022-03-28T18:00:51Z)
• Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning [44.38215560989223]
  Most existing knowledge graph embedding methods assume that all the triple facts in KGs are correct. This will lead to low-quality and unreliable representations of KGs. We propose a general multi-task reinforcement learning framework, which can greatly alleviate the noisy data problem.
  arXiv  Detail & Related papers  (2021-11-11T08:51:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.