Self-supervised Graph Neural Networks via Diverse and Interactive Message Passing
Published in AAAI, 2022
| By interpreting Graph Neural Networks (GNNs) as the message passing from the spatial perspective, their success is attributed to Laplacian smoothing. However, it also leads to serious over-smoothing issue by stacking many layers. Recently, many efforts have been paid to overcome this issue in semi-supervised learning. Unfortunately, it is more serious in unsupervised node representation learning task due to the lack of supervision information. Thus, most of the unsupervised or self-supervised GNNs often employ onelayer GCN as the encoder. Essentially, the over-smoothing issue is caused by the over-simplification of the existing message passing, which possesses two intrinsic limits: blind message and uniform passing. |  |
Recommended citation: Liang Yang, Cheng Chen, Weixun Li, Bingxin Niu, Junhua Gu,, Chuan Wang, Dongxiao He, Yuanfang Guo, Xiaochun Cao. Self-supervised Graph Neural Networks via Diverse and Interactive Message Passing. AAAI-22.