TY - JOUR
T1 - Neighborhood Attention Networks with Adversarial Learning for Link Prediction
AU - Wang, Zhitao
AU - Lei, Yu
AU - Li, Wenjie
N1 - Funding Information:
Manuscript received May 6, 2019; revised February 19, 2020 and July 2, 2020; accepted August 4, 2020. Date of publication August 24, 2020; date of current version August 4, 2021. This work was supported in part by the National Natural Science Foundation of China under Grant 61672445 and in part by the Research Grants Council of Hong Kong under Grant PolyU 15204018 and Grant PolyU 15210919. (Corresponding author: Yu Lei.) The authors are with the Department of Computing, The Hong Kong Polytechnic University, Hong Kong (e-mail: [email protected]; [email protected]; [email protected]).
Publisher Copyright:
© 2012 IEEE.
PY - 2021/8
Y1 - 2021/8
N2 - In this article, we aim at developing neighborhood-based neural models for link prediction. We design a novel multispace neighbor attention mechanism to extract universal neighborhood features by capturing latent importance of neighbors and selectively aggregate their features in multiple latent spaces. Grounded on this mechanism, we propose two link prediction models, i.e., self neighborhood attention network (SNAN), which predicts the link of two nodes by encoding and matching their respective neighborhood information, and its extension cross neighborhood attention network (CNAN), where we additionally design a cross neighborhood attention to directly capture structural interactions between two nodes. Another key novelty of this work is that we propose an adversarial learning framework, where a negative sample generator is devised to improve the optimization of the proposed link prediction models by continuously providing highly informative negative samples in the adversarial game. We evaluate our models with extensive experiments on 12 benchmark data sets against 14 popular and state-of-the-art link prediction approaches. The results strongly demonstrate the significant and universal superiority of our models on various types of networks. The effectiveness and robustness of the proposed attention mechanism and adversarial learning framework are also verified by detailed ablation studies.
AB - In this article, we aim at developing neighborhood-based neural models for link prediction. We design a novel multispace neighbor attention mechanism to extract universal neighborhood features by capturing latent importance of neighbors and selectively aggregate their features in multiple latent spaces. Grounded on this mechanism, we propose two link prediction models, i.e., self neighborhood attention network (SNAN), which predicts the link of two nodes by encoding and matching their respective neighborhood information, and its extension cross neighborhood attention network (CNAN), where we additionally design a cross neighborhood attention to directly capture structural interactions between two nodes. Another key novelty of this work is that we propose an adversarial learning framework, where a negative sample generator is devised to improve the optimization of the proposed link prediction models by continuously providing highly informative negative samples in the adversarial game. We evaluate our models with extensive experiments on 12 benchmark data sets against 14 popular and state-of-the-art link prediction approaches. The results strongly demonstrate the significant and universal superiority of our models on various types of networks. The effectiveness and robustness of the proposed attention mechanism and adversarial learning framework are also verified by detailed ablation studies.
KW - Adversarial learning
KW - link prediction
KW - neighborhood attention networks (NANs)
UR - http://www.scopus.com/inward/record.url?scp=85111966577&partnerID=8YFLogxK
U2 - 10.1109/TNNLS.2020.3015896
DO - 10.1109/TNNLS.2020.3015896
M3 - Journal article
C2 - 32833651
AN - SCOPUS:85111966577
SN - 2162-237X
VL - 32
SP - 3653
EP - 3663
JO - IEEE Transactions on Neural Networks and Learning Systems
JF - IEEE Transactions on Neural Networks and Learning Systems
IS - 8
M1 - 9174790
ER -