Constructing Graph Node Embeddings via Discrimination of Similarity Distributions

被引：1

作者：

Tsepa, Stanislav ^{[1
]}

Panov, Maxim ^{[2
]}

机构：

[1] RAS, Skolkovo Inst Sci & Technol Skoltech, Moscow Inst Phys & Technol, Inst Informat Transmiss Problems, Moscow, Russia

[2] RAS, Skolkovo Inst Sci & Technol Skoltech, Inst Informat Transmiss Problems, Moscow, Russia

来源：

2018 18TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS (ICDMW) | 2018年

基金：

俄罗斯科学基金会;

关键词：

Graph node embeddings; representation learning; Wasserstein distance; unsupervised learning; link prediction;

D O I：

10.1109/ICDMW.2018.00152

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The problem of unsupervised learning node embeddings in graphs is one of the important directions in modern network science. In this work we propose a novel framework, which is aimed to find embeddings by discriminating distributions of similarities (DDoS) between nodes in the graph. The general idea is implemented by maximizing the earth mover distance between distributions of decoded similarities of similar and dissimilar nodes. The resulting algorithm generates embeddings which give a state-of-the-art performance in the problem of link prediction in real-world graphs.

引用

页码：1050 / 1053

页数：4

共 50 条

[31] EmbedJoin: Efficient Edit Similarity Joins via Embeddings
Zhang, Haoyu
Zhang, Qin
KDD'17: PROCEEDINGS OF THE 23RD ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2017, : 585 - 594
[32] Managing Big Data by Directed Graph Node Similarity
Pap, Endre
Jocic, Marko
Szakal, Aniko
Obradovic, Djordje
Konjovic, Zora
2016 17TH IEEE INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE AND INFORMATICS (CINTI 2016), 2016, : 25 - 29
[33] Learning Structural Node Embeddings via Diffusion Wavelets
Donnat, Claire
Zitnik, Marinka
Hallac, David
Leskovec, Jure
KDD'18: PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2018, : 1320 - 1329
[34] Enhancing Graph Data Quality by Leveraging Heterogeneous Node Features and Embeddings
Angonese, Silvio Fernando
Galante, Renata
INTELLIGENT SYSTEMS, BRACIS 2024, PT I, 2025, 15412 : 383 - 398
[35] Learning from Conditional Distributions via Dual Embeddings
Dai, Bo
He, Niao
Pan, Yunpeng
Boots, Byron
Song, Le
ARTIFICIAL INTELLIGENCE AND STATISTICS, VOL 54, 2017, 54 : 1458 - 1467
[36] Knowledge Graph Embeddings with node2vec for Item Recommendation
Palumbo, Enrico
Rizzo, Giuseppe
Troncy, Raphael
Baralis, Elena
Osella, Michele
Ferro, Enrico
SEMANTIC WEB: ESWC 2018 SATELLITE EVENTS, 2018, 11155 : 117 - 120
[37] LONE SAMPLER : Graph Node Embeddings by Coordinated Local Neighborhood Sampling
Kutzkov, Konstantin
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 7, 2023, : 8413 - 8420
[38] Streaming Graph Embeddings via Incremental Neighborhood Sketching
Yang, Dingqi
Qu, Bingqing
Yang, Jie
Wang, Liang
Cudre-Mauroux, Philippe
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (05) : 5296 - 5310
[39] Scalable Graph Embeddings via Sparse Transpose Proximities
Yin, Yuan
Wei, Zhewei
KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2019, : 1429 - 1437
[40] A Provable Framework of Learning Graph Embeddings via Summarization
Zhou, Houquan
Liu, Shenghua
Koutra, Danai
Shen, Huawei
Cheng, Xueqi
THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 4, 2023, : 4946 - 4953

← 1 2 3 4 5 →