Geometric Pooling: maintaining more useful information
This work addresses a specific bottleneck in graph neural networks for node classification tasks, offering an incremental improvement over existing pooling technologies.
The paper tackled the problem of graph pooling in node classification by identifying that existing sorting pooling methods discard negative-value units containing useful information, and proposed Geometric Pooling (GP) to retain these features, resulting in a 1% to 5% performance improvement over state-of-the-art methods with fewer parameters.
Graph Pooling technology plays an important role in graph node classification tasks. Sorting pooling technologies maintain large-value units for pooling graphs of varying sizes. However, by analyzing the statistical characteristic of activated units after pooling, we found that a large number of units dropped by sorting pooling are negative-value units that contain useful information and can contribute considerably to the final decision. To maintain more useful information, a novel pooling technology, called Geometric Pooling (GP), was proposed to contain the unique node features with negative values by measuring the similarity of all node features. We reveal the effectiveness of GP from the entropy reduction view. The experiments were conducted on TUdatasets to show the effectiveness of GP. The results showed that the proposed GP outperforms the SOTA graph pooling technologies by 1%\sim5% with fewer parameters.