Graph Convolutional Network with Generalized Factorized Bilinear Aggregation

TL;DR

This paper introduces a generalized factorized bilinear layer for graph convolutional networks, enhancing their ability to model feature interactions while addressing overfitting and correlation issues, leading to improved text classification performance.

Contribution

It proposes a compact, generalized bilinear layer for GCNs that captures feature interactions more effectively and mitigates overfitting and correlation problems.

Findings

GFB-GCN performs competitively on multiple datasets.

The proposed layer improves modeling of feature interactions.

Addressed overfitting and correlation issues in GCNs.

Abstract

Although Graph Convolutional Networks (GCNs) have demonstrated their power in various applications, the graph convolutional layers, as the most important component of GCN, are still using linear transformations and a simple pooling step. In this paper, we propose a novel generalization of Factorized Bilinear (FB) layer to model the feature interactions in GCNs. FB performs two matrix-vector multiplications, that is, the weight matrix is multiplied with the outer product of the vector of hidden features from both sides. However, the FB layer suffers from the quadratic number of coefficients, overfitting and the spurious correlations due to correlations between channels of hidden representations that violate the i.i.d. assumption. Thus, we propose a compact FB layer by defining a family of summarizing operators applied over the quadratic term. We analyze proposed pooling operators and motivate their use. Our experimental results on multiple datasets demonstrate that the GFB-GCN is competitive with other methods for text classification.