GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs

TL;DR

GAIN introduces a novel graph neural network architecture that employs multiple aggregators with attention, a graph regularized loss, and feature interaction mechanisms to improve inductive learning on large-scale graphs, outperforming existing models.

Contribution

The paper proposes GAIN, a GNN model with multi-aggregator attention, graph regularized loss, and explicit feature interaction, enhancing expressive power and inductive learning capabilities.

Findings

GAIN outperforms state-of-the-art models on node classification tasks.

The multi-aggregator attention mechanism improves information capture.

Graph regularized loss enhances topological relationship modeling.

Abstract

Graph Neural Networks (GNNs) have led to state-of-the-art performance on a variety of machine learning tasks such as recommendation, node classification and link prediction. Graph neural network models generate node embeddings by merging nodes features with the aggregated neighboring nodes information. Most existing GNN models exploit a single type of aggregator (e.g., mean-pooling) to aggregate neighboring nodes information, and then add or concatenate the output of aggregator to the current representation vector of the center node. However, using only a single type of aggregator is difficult to capture the different aspects of neighboring information and the simple addition or concatenation update methods limit the expressive capability of GNNs. Not only that, existing supervised or semi-supervised GNN models are trained based on the loss function of the node label, which leads to the neglect of graph structure information. In this paper, we propose a novel graph neural network architecture, Graph Attention \& Interaction Network (GAIN), for inductive learning on graphs. Unlike the previous GNN models that only utilize a single type of aggregation method, we use multiple types of aggregators to gather neighboring information in different aspects and integrate the outputs of these aggregators through the aggregator-level attention mechanism. Furthermore, we design a graph regularized loss to better capture the topological relationship of the nodes in the graph. Additionally, we first present the concept of graph feature interaction and propose a vector-wise explicit feature interaction mechanism to update the node embeddings. We conduct comprehensive experiments on two node-classification benchmarks and a real-world financial news dataset. The experiments demonstrate our GAIN model outperforms current state-of-the-art performances on all the tasks.