BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks

Abstract

Graph convolutional networks (GCNs), aiming to integrate high-order neighborhood information through stacked graph convolution layers, have demonstrated remarkable power in many network analysis tasks. However, topological limitations, including over-smoothing and local topology homophily, limit its capability to represent networks. Existing studies only perform feature convolution on network topology, which inevitably introduces unbalance between topology and features. Considering that in real world, the information network consists of not only the node-level citation information but also the local text-sequence information. We propose BiTe-GCN, a novel GCN architecture with bidirectional convolution of both topology and features on text-rich networks to solve these limitations. We first transform the original text-rich network into an augmented bi-typed heterogeneous network, capturing both the global node-level information and the local text-sequence information from texts. We then introduce discriminative convolution mechanisms to performs convolutions of both topology and features simultaneously. Extensive experiments on text-rich networks demonstrate that our new architecture outperforms state-of-the-art by a breakout improvement. Moreover, this architecture can also be applied to several e-commerce searching scenes such as JD searching. The experiments on the JD dataset validate the superiority of the proposed architecture over the related methods.

arXiv commentWSDM 2021

References in corpus (18)

• Distributed Representations of Words and Phrases and their Compositionality
• Inductive Representation Learning on Large Graphs
• Simplifying Graph Convolutional Networks
• Convolutional Neural Network Architectures for Matching Natural Language Sentences
• Representation Learning on Graphs with Jumping Knowledge Networks
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• End-to-End Neural Ad-hoc Ranking with Kernel Pooling
• Attention-based Graph Neural Network for Semi-supervised Learning
• PairNorm: Tackling Oversmoothing in GNNs
• A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations
• Geom-GCN: Geometric Graph Convolutional Networks
• Position-aware Graph Neural Networks
• Spherical Text Embedding
• Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks
• Non-Local Graph Neural Networks
• Automated Phrase Mining from Massive Text Corpora
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
• Heterogeneous Network Embedding for Deep Semantic Relevance Match in E-commerce Search