GIPA: General Information Propagation Algorithm for Graph Learning

TL;DR

GIPA is a novel graph attention neural network that incorporates edge features and advanced attention mechanisms, achieving superior prediction accuracy on the ogbn-proteins dataset compared to existing models.

Contribution

The paper introduces GIPA, a new GNN with multi-head attention, edge feature propagation, and residual aggregation, advancing graph learning techniques.

Findings

GIPA outperforms previous models on the ogbn-proteins dataset.

Achieves an average ROC-AUC of 0.8700, surpassing state-of-the-art.

Incorporates edge features into propagation for improved accuracy.

Abstract

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.