Improving Inductive Link Prediction Using Hyper-Relational Facts

• URL: http://arxiv.org/abs/2107.04894v1
• Date: Sat, 10 Jul 2021 19:16:03 GMT
• Title: Improving Inductive Link Prediction Using Hyper-Relational Facts
• Authors: Mehdi Ali, Max Berrendorf, Mikhail Galkin, Veronika Thost, Tengfei Ma, Volker Tresp, Jens Lehmann
• Abstract summary: We study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by graph neural networks. Our experiments show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains.
• Score: 15.820005235333882
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: For many years, link prediction on knowledge graphs (KGs) has been a purely transductive task, not allowing for reasoning on unseen entities. Recently, increasing efforts are put into exploring semi- and fully inductive scenarios, enabling inference over unseen and emerging entities. Still, all these approaches only consider triple-based \glspl{kg}, whereas their richer counterparts, hyper-relational KGs (e.g., Wikidata), have not yet been properly studied. In this work, we classify different inductive settings and study the benefits of employing hyper-relational KGs on a wide range of semi- and fully inductive link prediction tasks powered by recent advancements in graph neural networks. Our experiments on a novel set of benchmarks show that qualifiers over typed edges can lead to performance improvements of 6% of absolute gains (for the Hits@10 metric) compared to triple-only baselines. Our code is available at \url{https://github.com/mali-git/hyper_relational_ilp}.

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)
• Towards Few-shot Inductive Link Prediction on Knowledge Graphs: A Relational Anonymous Walk-guided Neural Process Approach [49.00753238429618]
  Few-shot inductive link prediction on knowledge graphs aims to predict missing links for unseen entities with few-shot links observed. Recent inductive methods utilize the sub-graphs around unseen entities to obtain the semantics and predict links inductively. We propose a novel relational anonymous walk-guided neural process for few-shot inductive link prediction on knowledge graphs, denoted as RawNP.
  arXiv  Detail & Related papers  (2023-06-26T12:02:32Z)
• From Hypergraph Energy Functions to Hypergraph Neural Networks [94.88564151540459]
  We present an expressive family of parameterized, hypergraph-regularized energy functions. We then demonstrate how minimizers of these energies effectively serve as node embeddings. We draw parallels between the proposed bilevel hypergraph optimization, and existing GNN architectures in common use.
  arXiv  Detail & Related papers  (2023-06-16T04:40:59Z)
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion [69.55700751102376]
  Few-shot knowledge graph completion (FKGC) aims to predict missing facts for unseen relations with few-shot associated facts. Existing FKGC methods are based on metric learning or meta-learning, which often suffer from the out-of-distribution and overfitting problems. In this paper, we propose a normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC)
  arXiv  Detail & Related papers  (2023-04-17T11:42:28Z)
• Link Prediction with Non-Contrastive Learning [19.340519670329382]
  Graph self-supervised learning (SSL) aims to derive useful node representations without labeled data. Many state-of-the-art graph SSL methods are contrastive methods, which use a combination of positive and negative samples. Recent literature introduced non-contrastive methods, which instead only use positive samples.
  arXiv  Detail & Related papers  (2022-11-25T22:30:15Z)
• Relational Message Passing for Fully Inductive Knowledge Graph Completion [37.29833710603933]
  In knowledge graph completion (KGC), predicting triples involving emerging entities and/or relations, which are unseen when KG embeddings are learned, has become a critical challenge. Subgraph reasoning with message passing is a promising and popular solution. We propose a new method named RMPI which uses a novel Message Passing network for fully available KGC.
  arXiv  Detail & Related papers  (2022-10-08T10:35:52Z)
• 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)
• An Open Challenge for Inductive Link Prediction on Knowledge Graphs [0.7960322329952452]
  An emerging trend in representation learning over knowledge graphs (KGs) moves beyond transductive link prediction tasks. Despite the growing interest, there are not enough benchmarks for evaluating inductive representation learning methods. We introduce ILPC 2022, a novel open challenge on KG inductive link prediction.
  arXiv  Detail & Related papers  (2022-03-03T05:24:09Z)
• Message Passing for Hyper-Relational Knowledge Graphs [7.733963597282456]
  We propose a message passing graph encoder - StarE capable of modeling such hyper-relational knowledge graphs. StarE can encode an arbitrary number of additional information (qualifiers) along with the main triple while keeping the semantic roles of qualifiers and triples intact. Our experiments demonstrate that StarE based LP model outperforms existing approaches across multiple benchmarks.
  arXiv  Detail & Related papers  (2020-09-22T22:38:54Z)
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction [69.1473775184952]
  We introduce a realistic problem of few-shot out-of-graph link prediction. We tackle this problem with a novel transductive meta-learning framework. We validate our model on multiple benchmark datasets for knowledge graph completion and drug-drug interaction prediction.
  arXiv  Detail & Related papers  (2020-06-11T17:42:46Z)

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.