Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

Seongjun Yun; Seoyoon Kim; Junhyun Lee; Jaewoo Kang; Hyunwoo J. Kim

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

Seongjun Yun
, Seoyoon Kim
, Junhyun Lee
, Jaewoo Kang^*
, Hyunwoo J. Kim

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

131 Citations (Scopus)

Abstract

Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data. They have shown significant improvements over traditional heuristic methods in various tasks such as node classification and graph classification. However, since GNNs heavily rely on smoothed node features rather than graph structure, they often show poor performance than simple heuristic methods in link prediction where the structural information, e.g., overlapped neighborhoods, degrees, and shortest paths, is crucial. To address this limitation, we propose Neighborhood Overlap-aware Graph Neural Networks (Neo-GNNs) that learn useful structural features from an adjacency matrix and estimate overlapped neighborhoods for link prediction. Our Neo-GNNs generalize neighborhood overlap-based heuristic methods and handle overlapped multi-hop neighborhoods. Our extensive experiments on Open Graph Benchmark datasets (OGB) demonstrate that Neo-GNNs consistently achieve state-of-the-art performance in link prediction.

Original language	English
Title of host publication	Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021
Editors	Marc'Aurelio Ranzato, Alina Beygelzimer, Yann Dauphin, Percy S. Liang, Jenn Wortman Vaughan
Publisher	Neural information processing systems foundation
Pages	13683-13694
Number of pages	12
ISBN (Electronic)	9781713845393
Publication status	Published - 2021
Event	35th Conference on Neural Information Processing Systems, NeurIPS 2021 - Virtual, Online Duration: 2021 Dec 6 → 2021 Dec 14

Publication series

Name	Advances in Neural Information Processing Systems
Volume	17
ISSN (Print)	1049-5258

Conference

Conference	35th Conference on Neural Information Processing Systems, NeurIPS 2021
City	Virtual, Online
Period	21/12/6 → 21/12/14

Bibliographical note

Funding Information:
This work was supported by the following funding sources: National Research Foundation of Korea (NRF-2020R1A2C3010638, NRF-2014M3C9A3063541); ICT Creative Consilience program(IITP-2021-2020-0-01819) supervised by the IITP; Samsung Research Funding & Incubation Center of Samsung Electronics under Project Number SRFC-IT1701-51.

Publisher Copyright:
© 2021 Neural information processing systems foundation. All rights reserved.

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

Cite this

Yun, S., Kim, S., Lee, J., Kang, J., & Kim, H. J. (2021). Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction. In MA. Ranzato, A. Beygelzimer, Y. Dauphin, P. S. Liang, & J. Wortman Vaughan (Eds.), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021 (pp. 13683-13694). (Advances in Neural Information Processing Systems; Vol. 17). Neural information processing systems foundation.

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction. / Yun, Seongjun; Kim, Seoyoon; Lee, Junhyun et al.
Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. ed. / Marc'Aurelio Ranzato; Alina Beygelzimer; Yann Dauphin; Percy S. Liang; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. p. 13683-13694 (Advances in Neural Information Processing Systems; Vol. 17).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Yun, S, Kim, S, Lee, J, Kang, J & Kim, HJ 2021, Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction. in MA Ranzato, A Beygelzimer, Y Dauphin, PS Liang & J Wortman Vaughan (eds), Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Advances in Neural Information Processing Systems, vol. 17, Neural information processing systems foundation, pp. 13683-13694, 35th Conference on Neural Information Processing Systems, NeurIPS 2021, Virtual, Online, 21/12/6.

Yun S, Kim S, Lee J, Kang J, Kim HJ. Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction. In Ranzato MA, Beygelzimer A, Dauphin Y, Liang PS, Wortman Vaughan J, editors, Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. Neural information processing systems foundation. 2021. p. 13683-13694. (Advances in Neural Information Processing Systems).

Yun, Seongjun ; Kim, Seoyoon ; Lee, Junhyun et al. / Neo-GNNs : Neighborhood Overlap-aware Graph Neural Networks for Link Prediction. Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021. editor / Marc'Aurelio Ranzato ; Alina Beygelzimer ; Yann Dauphin ; Percy S. Liang ; Jenn Wortman Vaughan. Neural information processing systems foundation, 2021. pp. 13683-13694 (Advances in Neural Information Processing Systems).

@inproceedings{df34f003efe843419ed64bf88a5851d6,

title = "Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction",

abstract = "Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data. They have shown significant improvements over traditional heuristic methods in various tasks such as node classification and graph classification. However, since GNNs heavily rely on smoothed node features rather than graph structure, they often show poor performance than simple heuristic methods in link prediction where the structural information, e.g., overlapped neighborhoods, degrees, and shortest paths, is crucial. To address this limitation, we propose Neighborhood Overlap-aware Graph Neural Networks (Neo-GNNs) that learn useful structural features from an adjacency matrix and estimate overlapped neighborhoods for link prediction. Our Neo-GNNs generalize neighborhood overlap-based heuristic methods and handle overlapped multi-hop neighborhoods. Our extensive experiments on Open Graph Benchmark datasets (OGB) demonstrate that Neo-GNNs consistently achieve state-of-the-art performance in link prediction.",

author = "Seongjun Yun and Seoyoon Kim and Junhyun Lee and Jaewoo Kang and Kim, \{Hyunwoo J.\}",

note = "Funding Information: This work was supported by the following funding sources: National Research Foundation of Korea (NRF-2020R1A2C3010638, NRF-2014M3C9A3063541); ICT Creative Consilience program(IITP-2021-2020-0-01819) supervised by the IITP; Samsung Research Funding \& Incubation Center of Samsung Electronics under Project Number SRFC-IT1701-51. Publisher Copyright: {\textcopyright} 2021 Neural information processing systems foundation. All rights reserved.; 35th Conference on Neural Information Processing Systems, NeurIPS 2021 ; Conference date: 06-12-2021 Through 14-12-2021",

year = "2021",

language = "English",

series = "Advances in Neural Information Processing Systems",

publisher = "Neural information processing systems foundation",

pages = "13683--13694",

editor = "Marc'Aurelio Ranzato and Alina Beygelzimer and Yann Dauphin and Liang, \{Percy S.\} and \{Wortman Vaughan\}, Jenn",

booktitle = "Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021",

}

TY - GEN

T1 - Neo-GNNs

T2 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

AU - Yun, Seongjun

AU - Kim, Seoyoon

AU - Lee, Junhyun

AU - Kang, Jaewoo

AU - Kim, Hyunwoo J.

N1 - Funding Information: This work was supported by the following funding sources: National Research Foundation of Korea (NRF-2020R1A2C3010638, NRF-2014M3C9A3063541); ICT Creative Consilience program(IITP-2021-2020-0-01819) supervised by the IITP; Samsung Research Funding & Incubation Center of Samsung Electronics under Project Number SRFC-IT1701-51. Publisher Copyright: © 2021 Neural information processing systems foundation. All rights reserved.

PY - 2021

Y1 - 2021

N2 - Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data. They have shown significant improvements over traditional heuristic methods in various tasks such as node classification and graph classification. However, since GNNs heavily rely on smoothed node features rather than graph structure, they often show poor performance than simple heuristic methods in link prediction where the structural information, e.g., overlapped neighborhoods, degrees, and shortest paths, is crucial. To address this limitation, we propose Neighborhood Overlap-aware Graph Neural Networks (Neo-GNNs) that learn useful structural features from an adjacency matrix and estimate overlapped neighborhoods for link prediction. Our Neo-GNNs generalize neighborhood overlap-based heuristic methods and handle overlapped multi-hop neighborhoods. Our extensive experiments on Open Graph Benchmark datasets (OGB) demonstrate that Neo-GNNs consistently achieve state-of-the-art performance in link prediction.

AB - Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data. They have shown significant improvements over traditional heuristic methods in various tasks such as node classification and graph classification. However, since GNNs heavily rely on smoothed node features rather than graph structure, they often show poor performance than simple heuristic methods in link prediction where the structural information, e.g., overlapped neighborhoods, degrees, and shortest paths, is crucial. To address this limitation, we propose Neighborhood Overlap-aware Graph Neural Networks (Neo-GNNs) that learn useful structural features from an adjacency matrix and estimate overlapped neighborhoods for link prediction. Our Neo-GNNs generalize neighborhood overlap-based heuristic methods and handle overlapped multi-hop neighborhoods. Our extensive experiments on Open Graph Benchmark datasets (OGB) demonstrate that Neo-GNNs consistently achieve state-of-the-art performance in link prediction.

UR - https://www.scopus.com/pages/publications/85132029527

M3 - Conference contribution

AN - SCOPUS:85132029527

T3 - Advances in Neural Information Processing Systems

SP - 13683

EP - 13694

BT - Advances in Neural Information Processing Systems 34 - 35th Conference on Neural Information Processing Systems, NeurIPS 2021

A2 - Ranzato, Marc'Aurelio

A2 - Beygelzimer, Alina

A2 - Dauphin, Yann

A2 - Liang, Percy S.

A2 - Wortman Vaughan, Jenn

PB - Neural information processing systems foundation

Y2 - 6 December 2021 through 14 December 2021

ER -

Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this