SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs
- URL: http://arxiv.org/abs/2203.01044v1
- Date: Wed, 2 Mar 2022 11:40:37 GMT
- Title: SelfKG: Self-Supervised Entity Alignment in Knowledge Graphs
- Authors: Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov,
Yuxiao Dong, Jie Tang
- Abstract summary: We develop a self-supervised learning objective for entity alignment called SelfKG.
We show that SelfKG can match or achieve comparable results with state-of-the-art supervised baselines.
The performance of SelfKG suggests that self-supervised learning offers great potential for entity alignment in KGs.
- Score: 24.647609970140095
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Entity alignment, aiming to identify equivalent entities across different
knowledge graphs (KGs), is a fundamental problem for constructing Web-scale
KGs. Over the course of its development, the label supervision has been
considered necessary for accurate alignments. Inspired by the recent progress
of self-supervised learning, we explore the extent to which we can get rid of
supervision for entity alignment. Commonly, the label information (positive
entity pairs) is used to supervise the process of pulling the aligned entities
in each positive pair closer. However, our theoretical analysis suggests that
the learning of entity alignment can actually benefit more from pushing
unlabeled negative pairs far away from each other than pulling labeled positive
pairs close. By leveraging this discovery, we develop the self-supervised
learning objective for entity alignment. We present SelfKG with efficient
strategies to optimize this objective for aligning entities without label
supervision. Extensive experiments on benchmark datasets demonstrate that
SelfKG without supervision can match or achieve comparable results with
state-of-the-art supervised baselines. The performance of SelfKG suggests that
self-supervised learning offers great potential for entity alignment in KGs.
The code and data are available at https://github.com/THUDM/SelfKG.
Related papers
- One-bit Supervision for Image Classification: Problem, Solution, and
Beyond [114.95815360508395]
This paper presents one-bit supervision, a novel setting of learning with fewer labels, for image classification.
We propose a multi-stage training paradigm and incorporate negative label suppression into an off-the-shelf semi-supervised learning algorithm.
In multiple benchmarks, the learning efficiency of the proposed approach surpasses that using full-bit, semi-supervised supervision.
arXiv Detail & Related papers (2023-11-26T07:39:00Z) - A Fused Gromov-Wasserstein Framework for Unsupervised Knowledge Graph
Entity Alignment [22.526341223786375]
In this paper, we introduce FGWEA, an unsupervised entity alignment framework that leverages the Fused Gromov-Wasserstein (FGW) distance.
We show that FGWEA surpasses 21 competitive baselines, including cutting-edge supervised entity alignment methods.
arXiv Detail & Related papers (2023-05-11T05:17:54Z) - Deep Active Alignment of Knowledge Graph Entities and Schemata [20.100378168629195]
We propose a new KG alignment approach, called DAAKG, based on deep learning and active learning.
With deep learning, it learns the embeddings of entities, relations and classes, and jointly aligns them in a semi-supervised manner.
With active learning, it estimates how likely an entity, relation or class pair can be inferred, and selects the best batch for human labeling.
arXiv Detail & Related papers (2023-04-10T05:31:24Z) - ICLEA: Interactive Contrastive Learning for Self-supervised Entity
Alignment [27.449414854756913]
Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without seed alignments.
The current SOTA self-supervised EA method draws inspiration from contrastive learning, originally designed in computer vision.
We propose an interactive contrastive learning model for self-supervised EA.
arXiv Detail & Related papers (2022-01-17T06:04:00Z) - A Self-supervised Method for Entity Alignment [20.368788592613466]
Entity alignment is a fundamental problem for constructing large-scale knowledge graphs (KGs)
Inspired by the recent progress of self-supervised learning, we explore the extent to which we can get rid of supervision for entity alignment.
We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs.
arXiv Detail & Related papers (2021-06-17T11:22:20Z) - Towards Entity Alignment in the Open World: An Unsupervised Approach [29.337157862514204]
It is a pivotal step for integrating knowledge graphs (KGs) to increase knowledge coverage and quality.
State-of-the-art solutions tend to rely on labeled data for model training.
We offer an unsupervised framework that performs entity alignment in the open world.
arXiv Detail & Related papers (2021-01-26T03:10:24Z) - Can Semantic Labels Assist Self-Supervised Visual Representation
Learning? [194.1681088693248]
We present a new algorithm named Supervised Contrastive Adjustment in Neighborhood (SCAN)
In a series of downstream tasks, SCAN achieves superior performance compared to previous fully-supervised and self-supervised methods.
Our study reveals that semantic labels are useful in assisting self-supervised methods, opening a new direction for the community.
arXiv Detail & Related papers (2020-11-17T13:25:00Z) - Visual Pivoting for (Unsupervised) Entity Alignment [93.82387952905756]
This work studies the use of visual semantic representations to align entities in heterogeneous knowledge graphs (KGs)
We show that the proposed new approach, EVA, creates a holistic entity representation that provides strong signals for cross-graph entity alignment.
arXiv Detail & Related papers (2020-09-28T20:09:40Z) - Inductive Learning on Commonsense Knowledge Graph Completion [89.72388313527296]
Commonsense knowledge graph (CKG) is a special type of knowledge graph (CKG) where entities are composed of free-form text.
We propose to study the inductive learning setting for CKG completion where unseen entities may present at test time.
InductivE significantly outperforms state-of-the-art baselines in both standard and inductive settings on ATOMIC and ConceptNet benchmarks.
arXiv Detail & Related papers (2020-09-19T16:10:26Z) - Cross-lingual Entity Alignment with Incidental Supervision [76.66793175159192]
We propose an incidentally supervised model, JEANS, which jointly represents multilingual KGs and text corpora in a shared embedding scheme.
Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision.
arXiv Detail & Related papers (2020-05-01T01:53:56Z) - Embedding Graph Auto-Encoder for Graph Clustering [90.8576971748142]
Graph auto-encoder (GAE) models are based on semi-supervised graph convolution networks (GCN)
We design a specific GAE-based model for graph clustering to be consistent with the theory, namely Embedding Graph Auto-Encoder (EGAE)
EGAE consists of one encoder and dual decoders.
arXiv Detail & Related papers (2020-02-20T09:53:28Z)
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.