Confidence-Based Feature Imputation for Graphs with Partially Known Features
This addresses a critical bottleneck in graph learning for domains with incomplete data, offering a robust solution for high missing rates, though it is incremental in improving existing imputation methods.
The paper tackles the problem of missing feature imputation in graph learning tasks, particularly at high missing rates, by introducing a channel-wise confidence concept and a diffusion-based imputation scheme, achieving state-of-the-art accuracy on node classification and link prediction with up to 99.5% missing features.
This paper investigates a missing feature imputation problem for graph learning tasks. Several methods have previously addressed learning tasks on graphs with missing features. However, in cases of high rates of missing features, they were unable to avoid significant performance degradation. To overcome this limitation, we introduce a novel concept of channel-wise confidence in a node feature, which is assigned to each imputed channel feature of a node for reflecting certainty of the imputation. We then design pseudo-confidence using the channel-wise shortest path distance between a missing-feature node and its nearest known-feature node to replace unavailable true confidence in an actual learning process. Based on the pseudo-confidence, we propose a novel feature imputation scheme that performs channel-wise inter-node diffusion and node-wise inter-channel propagation. The scheme can endure even at an exceedingly high missing rate (e.g., 99.5\%) and it achieves state-of-the-art accuracy for both semi-supervised node classification and link prediction on various datasets containing a high rate of missing features. Codes are available at https://github.com/daehoum1/pcfi.