Dual Consistency Constraint-Based Self-Supervised Representation Learning for Heterogeneous Graphs With Missing Attributes

Missing attribute completion for unattributed nodes in heterogeneous graphs has received increasing attention, but previous works still suffer from the following issues: 1) they ignore the noise in the raw attributes, resulting in noise propagation and even inaccurate information generation during attribute completion, thus further influencing the representation learning; and 2) they ignore constraints on unattributed nodes when conducting consistency learning across augmented graph views, resulting in data inconsistency across views. To solve these issues, in this article, we propose a new dual consistency constraint-based self-supervised representation learning method for heterogeneous graphs with missing attributes. Specifically, we first investigate the representation completion and the within-view consistency loss to complete missing information in the representation space, and then, we investigate the cross-view consistency loss to ensure data consistency across views. We further reconstruct the masked data to avoid information loss due to the masking process. As a result, our method effectively filters out noise and inaccurate information by the representation completion process as well as achieves discriminative representation learning for heterogeneous graphs with missing attributes. Experimental results on various downstream tasks verify the superiority of our method.