NP$^2$L: Negative Pseudo Partial Labels Extraction for Graph Neural Networks
This addresses the issue of pseudo label accuracy in graph learning, offering a domain-specific improvement for GNN applications.
The paper tackles the problem of inaccurate pseudo labels in graph neural networks by proposing a method to extract negative pseudo partial labels, which are used to construct a signed graph that improves learning at the message-passing level, achieving state-of-the-art performance on link prediction and node classification tasks.
How to utilize the pseudo labels has always been a research hotspot in machine learning. However, most methods use pseudo labels as supervised training, and lack of valid assessing for their accuracy. Moreover, applications of pseudo labels in graph neural networks (GNNs) oversee the difference between graph learning and other machine learning tasks such as message passing mechanism. Aiming to address the first issue, we found through a large number of experiments that the pseudo labels are more accurate if they are selected by not overlapping partial labels and defined as negative node pairs relations. Therefore, considering the extraction based on pseudo and partial labels, negative edges are constructed between two nodes by the negative pseudo partial labels extraction (NP$^2$E) module. With that, a signed graph are built containing highly accurate pseudo labels information from the original graph, which effectively assists GNN in learning at the message-passing level, provide one solution to the second issue. Empirical results about link prediction and node classification tasks on several benchmark datasets demonstrate the effectiveness of our method. State-of-the-art performance is achieved on the both tasks.