@inproceedings{ahrabian-etal-2020-structure,
title = "Structure Aware Negative Sampling in Knowledge Graphs",
author = "Ahrabian, Kian and
Feizi, Aarash and
Salehi, Yasmin and
Hamilton, William L. and
Bose, Avishek Joey",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.492",
doi = "10.18653/v1/2020.emnlp-main.492",
pages = "6093--6101",
abstract = "Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches is the choice of corruption distribution that generates hard negative samples, which force the embedding model to learn discriminative representations and find critical characteristics of observed data. While earlier methods either employ too simple corruption distributions, i.e. uniform, yielding easy uninformative negatives or sophisticated adversarial distributions with challenging optimization schemes, they do not explicitly incorporate known graph structure resulting in suboptimal negatives. In this paper, we propose Structure Aware Negative Sampling (SANS), an inexpensive negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node{'}s $k$-hop neighborhood. Empirically, we demonstrate that SANS finds semantically meaningful negatives and is competitive with SOTA approaches while requires no additional parameters nor difficult adversarial optimization.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ahrabian-etal-2020-structure">
<titleInfo>
<title>Structure Aware Negative Sampling in Knowledge Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kian</namePart>
<namePart type="family">Ahrabian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aarash</namePart>
<namePart type="family">Feizi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasmin</namePart>
<namePart type="family">Salehi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Hamilton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Avishek</namePart>
<namePart type="given">Joey</namePart>
<namePart type="family">Bose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches is the choice of corruption distribution that generates hard negative samples, which force the embedding model to learn discriminative representations and find critical characteristics of observed data. While earlier methods either employ too simple corruption distributions, i.e. uniform, yielding easy uninformative negatives or sophisticated adversarial distributions with challenging optimization schemes, they do not explicitly incorporate known graph structure resulting in suboptimal negatives. In this paper, we propose Structure Aware Negative Sampling (SANS), an inexpensive negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node’s k-hop neighborhood. Empirically, we demonstrate that SANS finds semantically meaningful negatives and is competitive with SOTA approaches while requires no additional parameters nor difficult adversarial optimization.</abstract>
<identifier type="citekey">ahrabian-etal-2020-structure</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.492</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.492</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>6093</start>
<end>6101</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Structure Aware Negative Sampling in Knowledge Graphs
%A Ahrabian, Kian
%A Feizi, Aarash
%A Salehi, Yasmin
%A Hamilton, William L.
%A Bose, Avishek Joey
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ahrabian-etal-2020-structure
%X Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches is the choice of corruption distribution that generates hard negative samples, which force the embedding model to learn discriminative representations and find critical characteristics of observed data. While earlier methods either employ too simple corruption distributions, i.e. uniform, yielding easy uninformative negatives or sophisticated adversarial distributions with challenging optimization schemes, they do not explicitly incorporate known graph structure resulting in suboptimal negatives. In this paper, we propose Structure Aware Negative Sampling (SANS), an inexpensive negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node’s k-hop neighborhood. Empirically, we demonstrate that SANS finds semantically meaningful negatives and is competitive with SOTA approaches while requires no additional parameters nor difficult adversarial optimization.
%R 10.18653/v1/2020.emnlp-main.492
%U https://aclanthology.org/2020.emnlp-main.492
%U https://doi.org/10.18653/v1/2020.emnlp-main.492
%P 6093-6101
Markdown (Informal)
[Structure Aware Negative Sampling in Knowledge Graphs](https://aclanthology.org/2020.emnlp-main.492) (Ahrabian et al., EMNLP 2020)
ACL
- Kian Ahrabian, Aarash Feizi, Yasmin Salehi, William L. Hamilton, and Avishek Joey Bose. 2020. Structure Aware Negative Sampling in Knowledge Graphs. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6093–6101, Online. Association for Computational Linguistics.