GIPA: General Information Propagation Algorithm for Graph Learning
This work addresses graph learning for tasks like node classification and link prediction, offering an incremental improvement over existing methods by incorporating edge features and enhanced attention mechanisms.
The paper tackles the problem of learning from attributed graph data by proposing GIPA, a new graph attention neural network that incorporates attention, feature propagation, and aggregation components, achieving state-of-the-art results with an average test ROC-AUC of 0.8700±0.0010 on the ogbn-proteins dataset.
Graph neural networks (GNNs) have been popularly used in analyzing graph-structured data, showing promising results in various applications such as node classification, link prediction and network recommendation. In this paper, we present a new graph attention neural network, namely GIPA, for attributed graph data learning. GIPA consists of three key components: attention, feature propagation and aggregation. Specifically, the attention component introduces a new multi-layer perceptron based multi-head to generate better non-linear feature mapping and representation than conventional implementations such as dot-product. The propagation component considers not only node features but also edge features, which differs from existing GNNs that merely consider node features. The aggregation component uses a residual connection to generate the final embedding. We evaluate the performance of GIPA using the Open Graph Benchmark proteins (ogbn-proteins for short) dataset. The experimental results reveal that GIPA can beat the state-of-the-art models in terms of prediction accuracy, e.g., GIPA achieves an average test ROC-AUC of $0.8700\pm 0.0010$ and outperforms all the previous methods listed in the ogbn-proteins leaderboard.