AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning

Yongqi Zhang; Zhanke Zhou; Quanming Yao; Xiaowen Chu; Bo Han

doi:10.1145/3580305.3599404

AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning

Yongqi Zhang, Zhanke Zhou, Quanming Yao^*, Xiaowen Chu, Bo Han

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

27 Citations (Scopus)

Abstract

Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step. Existing methods use hand-designed propagation paths, ignoring the correlation between the entities and the query relation. In addition, the number of involved entities will explosively grow at larger propagation steps. In this work, we are motivated to learn an adaptive propagation path in order to filter out irrelevant entities while preserving promising targets. First, we design an incremental sampling mechanism where the nearby targets and layer-wise connections can be preserved with linear complexity. Second, we design a learning-based sampling distribution to identify the semantically related entities. Extensive experiments show that our method is powerful, efficient and semantic-aware. The code is available at https://github.com/LARS-research/AdaProp.

Original language	English
Title of host publication	KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
Publisher	Association for Computing Machinery (ACM)
Pages	3446-3457
Number of pages	12
ISBN (Electronic)	9798400701030
DOIs	https://doi.org/10.1145/3580305.3599404
Publication status	Published - 4 Aug 2023
Event	29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 - Long Beach, United States Duration: 6 Aug 2023 → 10 Aug 2023 https://kdd.org/kdd2023/ https://dl.acm.org/doi/proceedings/10.1145/3580305

Publication series

Name	Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

Conference

Conference	29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023
Country/Territory	United States
City	Long Beach
Period	6/08/23 → 10/08/23
Internet address	https://kdd.org/kdd2023/ https://dl.acm.org/doi/proceedings/10.1145/3580305

Scopus Subject Areas

Software
Information Systems

User-Defined Keywords

graph embedding
graph neural network
graph sampling
knowledge graph
knowledge graph reasoning

Access to Document

10.1145/3580305.3599404

Cite this

Zhang, Y., Zhou, Z., Yao, Q., Chu, X., & Han, B. (2023). AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning. In KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 3446-3457). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). Association for Computing Machinery (ACM). https://doi.org/10.1145/3580305.3599404

Zhang, Yongqi ; Zhou, Zhanke ; Yao, Quanming et al. / AdaProp : Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning. KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM), 2023. pp. 3446-3457 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

@inproceedings{f838c680773c4df5a2c514b0b9f30dbf,

title = "AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning",

abstract = "Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step. Existing methods use hand-designed propagation paths, ignoring the correlation between the entities and the query relation. In addition, the number of involved entities will explosively grow at larger propagation steps. In this work, we are motivated to learn an adaptive propagation path in order to filter out irrelevant entities while preserving promising targets. First, we design an incremental sampling mechanism where the nearby targets and layer-wise connections can be preserved with linear complexity. Second, we design a learning-based sampling distribution to identify the semantically related entities. Extensive experiments show that our method is powerful, efficient and semantic-aware. The code is available at https://github.com/LARS-research/AdaProp.",

keywords = "graph embedding, graph neural network, graph sampling, knowledge graph, knowledge graph reasoning",

author = "Yongqi Zhang and Zhanke Zhou and Quanming Yao and Xiaowen Chu and Bo Han",

note = "Y. Zhang is supported by National Key Research and Development Plan under Grant 2021YFE0205700. Q. Yao is supported by NSF of China (No. 92270106) and Independent scientific research fund (Foshan advanced manufacturing research institute, Tsinghua University). Z. Zhou and B. Han are supported by NSFC Young Scientists Fund No. 62006202, Guangdong Basic and Applied Basic Research Foundation No. 2022A1515011652, and HKBU CSD Departmental Incentive Grant. Publisher Copyright: {\textcopyright} 2023 ACM.; 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023 ; Conference date: 06-08-2023 Through 10-08-2023",

year = "2023",

month = aug,

day = "4",

doi = "10.1145/3580305.3599404",

language = "English",

series = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",

publisher = "Association for Computing Machinery (ACM)",

pages = "3446--3457",

booktitle = "KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining",

address = "United States",

url = "https://kdd.org/kdd2023/, https://dl.acm.org/doi/proceedings/10.1145/3580305",

}

Zhang, Y, Zhou, Z, Yao, Q, Chu, X & Han, B 2023, AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning. in KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery (ACM), pp. 3446-3457, 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023, Long Beach, California, United States, 6/08/23. https://doi.org/10.1145/3580305.3599404

AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning. / Zhang, Yongqi; Zhou, Zhanke; Yao, Quanming et al.
KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM), 2023. p. 3446-3457 (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - AdaProp

T2 - 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023

AU - Zhang, Yongqi

AU - Zhou, Zhanke

AU - Yao, Quanming

AU - Chu, Xiaowen

AU - Han, Bo

N1 - Y. Zhang is supported by National Key Research and Development Plan under Grant 2021YFE0205700. Q. Yao is supported by NSF of China (No. 92270106) and Independent scientific research fund (Foshan advanced manufacturing research institute, Tsinghua University). Z. Zhou and B. Han are supported by NSFC Young Scientists Fund No. 62006202, Guangdong Basic and Applied Basic Research Foundation No. 2022A1515011652, and HKBU CSD Departmental Incentive Grant. Publisher Copyright: © 2023 ACM.

PY - 2023/8/4

Y1 - 2023/8/4

N2 - Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step. Existing methods use hand-designed propagation paths, ignoring the correlation between the entities and the query relation. In addition, the number of involved entities will explosively grow at larger propagation steps. In this work, we are motivated to learn an adaptive propagation path in order to filter out irrelevant entities while preserving promising targets. First, we design an incremental sampling mechanism where the nearby targets and layer-wise connections can be preserved with linear complexity. Second, we design a learning-based sampling distribution to identify the semantically related entities. Extensive experiments show that our method is powerful, efficient and semantic-aware. The code is available at https://github.com/LARS-research/AdaProp.

AB - Due to the popularity of Graph Neural Networks (GNNs), various GNN-based methods have been designed to reason on knowledge graphs (KGs). An important design component of GNN-based KG reasoning methods is called the propagation path, which contains a set of involved entities in each propagation step. Existing methods use hand-designed propagation paths, ignoring the correlation between the entities and the query relation. In addition, the number of involved entities will explosively grow at larger propagation steps. In this work, we are motivated to learn an adaptive propagation path in order to filter out irrelevant entities while preserving promising targets. First, we design an incremental sampling mechanism where the nearby targets and layer-wise connections can be preserved with linear complexity. Second, we design a learning-based sampling distribution to identify the semantically related entities. Extensive experiments show that our method is powerful, efficient and semantic-aware. The code is available at https://github.com/LARS-research/AdaProp.

KW - graph embedding

KW - graph neural network

KW - graph sampling

KW - knowledge graph

KW - knowledge graph reasoning

UR - http://www.scopus.com/inward/record.url?scp=85171328513&partnerID=8YFLogxK

U2 - 10.1145/3580305.3599404

DO - 10.1145/3580305.3599404

M3 - Conference proceeding

AN - SCOPUS:85171328513

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 3446

EP - 3457

BT - KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery (ACM)

Y2 - 6 August 2023 through 10 August 2023

ER -

Zhang Y, Zhou Z, Yao Q, Chu X, Han B. AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning. In KDD 2023 - Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery (ACM). 2023. p. 3446-3457. (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). doi: 10.1145/3580305.3599404

AdaProp: Learning Adaptive Propagation for Graph Neural Network based Knowledge Graph Reasoning

Abstract

Publication series

Conference

Scopus Subject Areas

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this