SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meng, Lingyuan, Liang, Ke, Xiao, Bin, Zhou, Sihang, Liu, Yue, Liu, Meng, Yang, Xihong, Liu, Xinwang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912086908469248
author Meng, Lingyuan
Liang, Ke
Xiao, Bin
Zhou, Sihang
Liu, Yue
Liu, Meng
Yang, Xihong
Liu, Xinwang
author_facet Meng, Lingyuan
Liang, Ke
Xiao, Bin
Zhou, Sihang
Liu, Yue
Liu, Meng
Yang, Xihong
Liu, Xinwang
contents Few-shot relation reasoning on knowledge graphs (FS-KGR) aims to infer long-tail data-poor relations, which has drawn increasing attention these years due to its practicalities. The pre-training of previous methods needs to manually construct the meta-relation set, leading to numerous labor costs. Self-supervised learning (SSL) is treated as a solution to tackle the issue, but still at an early stage for FS-KGR task. Moreover, most of the existing methods ignore leveraging the beneficial information from aliasing relations (AR), i.e., data-rich relations with similar contextual semantics to the target data-poor relation. Therefore, we proposed a novel Self-Supervised Learning model by leveraging Aliasing Relations to assist FS-KGR, termed SARF. Concretely, four main components are designed in our model, i.e., SSL reasoning module, AR-assisted mechanism, fusion module, and scoring function. We first generate the representation of the co-occurrence patterns in a generative manner. Meanwhile, the representations of aliasing relations are learned to enhance reasoning in the AR-assist mechanism. Besides, multiple strategies, i.e., simple summation and learnable fusion, are offered for representation fusion. Finally, the generated representation is used for scoring. Extensive experiments on three few-shot benchmarks demonstrate that SARF achieves state-of-the-art performance compared with other methods in most cases.
format Preprint
id arxiv_https___arxiv_org_abs_2304_10297
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning
Meng, Lingyuan
Liang, Ke
Xiao, Bin
Zhou, Sihang
Liu, Yue
Liu, Meng
Yang, Xihong
Liu, Xinwang
Machine Learning
Artificial Intelligence
Information Retrieval
Few-shot relation reasoning on knowledge graphs (FS-KGR) aims to infer long-tail data-poor relations, which has drawn increasing attention these years due to its practicalities. The pre-training of previous methods needs to manually construct the meta-relation set, leading to numerous labor costs. Self-supervised learning (SSL) is treated as a solution to tackle the issue, but still at an early stage for FS-KGR task. Moreover, most of the existing methods ignore leveraging the beneficial information from aliasing relations (AR), i.e., data-rich relations with similar contextual semantics to the target data-poor relation. Therefore, we proposed a novel Self-Supervised Learning model by leveraging Aliasing Relations to assist FS-KGR, termed SARF. Concretely, four main components are designed in our model, i.e., SSL reasoning module, AR-assisted mechanism, fusion module, and scoring function. We first generate the representation of the co-occurrence patterns in a generative manner. Meanwhile, the representations of aliasing relations are learned to enhance reasoning in the AR-assist mechanism. Besides, multiple strategies, i.e., simple summation and learnable fusion, are offered for representation fusion. Finally, the generated representation is used for scoring. Extensive experiments on three few-shot benchmarks demonstrate that SARF achieves state-of-the-art performance compared with other methods in most cases.
title SARF: Aliasing Relation Assisted Self-Supervised Learning for Few-shot Relation Reasoning
topic Machine Learning
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2304.10297