TY - GEN
T1 - MMAN
T2 - 36th AAAI Conference on Artificial Intelligence, AAAI 2022
AU - Liu, Jie
AU - Song, Lingyun
AU - Gao, Li
AU - Shang, Xuequn
N1 - Publisher Copyright:
Copyright © 2022, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2022/6/30
Y1 - 2022/6/30
N2 - Current Heterogeneous Network Embedding (HNE) models can be roughly divided into two types, i.e., relation-aware and metapath-aware models. However, they either fail to represent the non-pairwise relations in heterogeneous graph, or only capable of capturing local information around target node. In this paper, we propose a metapath based multilevel graph attention networks (MMAN) to jointly learn node embeddings on two substructures, i.e., metapath based graphs and hypergraphs extracted from original heterogeneous graph. Extensive experiments on three benchmark datasets for node classification and node clustering demonstrate the superiority of MMAN over the state-of-the-art works.
AB - Current Heterogeneous Network Embedding (HNE) models can be roughly divided into two types, i.e., relation-aware and metapath-aware models. However, they either fail to represent the non-pairwise relations in heterogeneous graph, or only capable of capturing local information around target node. In this paper, we propose a metapath based multilevel graph attention networks (MMAN) to jointly learn node embeddings on two substructures, i.e., metapath based graphs and hypergraphs extracted from original heterogeneous graph. Extensive experiments on three benchmark datasets for node classification and node clustering demonstrate the superiority of MMAN over the state-of-the-art works.
UR - http://www.scopus.com/inward/record.url?scp=85147604845&partnerID=8YFLogxK
U2 - 10.1609/aaai.v36i11.21639
DO - 10.1609/aaai.v36i11.21639
M3 - 会议稿件
AN - SCOPUS:85147604845
T3 - Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
SP - 13005
EP - 13006
BT - IAAI-22, EAAI-22, AAAI-22 Special Programs and Special Track, Student Papers and Demonstrations
PB - Association for the Advancement of Artificial Intelligence
Y2 - 22 February 2022 through 1 March 2022
ER -