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 - http://www.scopus.com/inward/record.url?scp=85132029527&partnerID=8YFLogxK
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 -