Robust Knowledge Graph Completion with Stacked Convolutions and a
Student Re-Ranking Network
- URL: http://arxiv.org/abs/2106.06555v1
- Date: Fri, 11 Jun 2021 18:01:27 GMT
- Title: Robust Knowledge Graph Completion with Stacked Convolutions and a
Student Re-Ranking Network
- Authors: Justin Lovelace, Denis Newman-Griffis, Shikhar Vashishth, Jill Fain
Lehman, Carolyn Penstein Ros\'e
- Abstract summary: We develop a deep convolutional network that utilizes textual entity representations.
We distill the knowledge from the convolutional network into a student network that re-ranks promising candidate entities.
This re-ranking stage leads to further improvements in performance and demonstrates the effectiveness of entity re-ranking for Knowledge Graph completion.
- Score: 6.952242545832663
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Knowledge Graph (KG) completion research usually focuses on densely connected
benchmark datasets that are not representative of real KGs. We curate two KG
datasets that include biomedical and encyclopedic knowledge and use an existing
commonsense KG dataset to explore KG completion in the more realistic setting
where dense connectivity is not guaranteed. We develop a deep convolutional
network that utilizes textual entity representations and demonstrate that our
model outperforms recent KG completion methods in this challenging setting. We
find that our model's performance improvements stem primarily from its
robustness to sparsity. We then distill the knowledge from the convolutional
network into a student network that re-ranks promising candidate entities. This
re-ranking stage leads to further improvements in performance and demonstrates
the effectiveness of entity re-ranking for KG completion.
Related papers
- GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion [52.026016846945424]
We propose a new method called GLTW, which encodes the structural information of KGs and merges it with Large Language Models.
Specifically, we introduce an improved Graph Transformer (iGT) that effectively encodes subgraphs with both local and global structural information.
Also, we develop a subgraph-based multi-classification training objective, using all entities within KG as classification objects, to boost learning efficiency.
arXiv Detail & Related papers (2025-02-17T06:02:59Z) - Distill-SynthKG: Distilling Knowledge Graph Synthesis Workflow for Improved Coverage and Efficiency [59.6772484292295]
Knowledge graphs (KGs) generated by large language models (LLMs) are increasingly valuable for Retrieval-Augmented Generation (RAG) applications.
Existing KG extraction methods rely on prompt-based approaches, which are inefficient for processing large-scale corpora.
We propose SynthKG, a multi-step, document-level synthesis KG workflow based on LLMs.
We also design a novel graph-based retrieval framework for RAG.
arXiv Detail & Related papers (2024-10-22T00:47:54Z) - KG-FIT: Knowledge Graph Fine-Tuning Upon Open-World Knowledge [63.19837262782962]
Knowledge Graph Embedding (KGE) techniques are crucial in learning compact representations of entities and relations within a knowledge graph.
This study introduces KG-FIT, which builds a semantically coherent hierarchical structure of entity clusters.
Experiments on the benchmark datasets FB15K-237, YAGO3-10, and PrimeKG demonstrate the superiority of KG-FIT over state-of-the-art pre-trained language model-based methods.
arXiv Detail & Related papers (2024-05-26T03:04:26Z) - 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) - 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) - Link-Intensive Alignment for Incomplete Knowledge Graphs [28.213397255810936]
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.
arXiv Detail & Related papers (2021-12-17T00:41:28Z) - Learning Intents behind Interactions with Knowledge Graph for
Recommendation [93.08709357435991]
Knowledge graph (KG) plays an increasingly important role in recommender systems.
Existing GNN-based models fail to identify user-item relation at a fine-grained level of intents.
We propose a new model, Knowledge Graph-based Intent Network (KGIN)
arXiv Detail & Related papers (2021-02-14T03:21:36Z) - FedE: Embedding Knowledge Graphs in Federated Setting [21.022513922373207]
Multi-Source KG is a common situation in real Knowledge Graph applications.
Because of the data privacy and sensitivity, a set of relevant knowledge graphs cannot complement each other's KGC by just collecting data from different knowledge graphs together.
We propose a Federated Knowledge Graph Embedding framework FedE, focusing on learning knowledge graph embeddings by aggregating locally-computed updates.
arXiv Detail & Related papers (2020-10-24T11:52:05Z) - Relational Learning Analysis of Social Politics using Knowledge Graph
Embedding [11.978556412301975]
This paper presents a novel credibility domain-based KG Embedding framework.
It involves capturing a fusion of data obtained from heterogeneous resources into a formal KG representation depicted by a domain.
The framework also embodies a credibility module to ensure data quality and trustworthiness.
arXiv Detail & Related papers (2020-06-02T14:10:28Z) - KACC: A Multi-task Benchmark for Knowledge Abstraction, Concretization
and Completion [99.47414073164656]
A comprehensive knowledge graph (KG) contains an instance-level entity graph and an ontology-level concept graph.
The two-view KG provides a testbed for models to "simulate" human's abilities on knowledge abstraction, concretization, and completion.
We propose a unified KG benchmark by improving existing benchmarks in terms of dataset scale, task coverage, and difficulty.
arXiv Detail & Related papers (2020-04-28T16:21:57Z)
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.