TeKo: Text-Rich Graph Neural Networks with External Knowledge

TL;DR

TeKo is a novel graph neural network that effectively integrates external structured and unstructured knowledge to enhance textual and structural understanding in text-rich networks, outperforming existing methods.

Contribution

Introduces a flexible heterogeneous semantic network and reciprocal convolutional mechanism to jointly leverage external knowledge and textual semantics in GNNs.

Findings

TeKo outperforms state-of-the-art baselines on four public datasets.

External knowledge integration improves semantic understanding.

Reciprocal convolution enhances network representation learning.

Abstract

Graph Neural Networks (GNNs) have gained great popularity in tackling various analytical tasks on graph-structured data (i.e., networks). Typical GNNs and their variants follow a message-passing manner that obtains network representations by the feature propagation process along network topology, which however ignore the rich textual semantics (e.g., local word-sequence) that exist in many real-world networks. Existing methods for text-rich networks integrate textual semantics by mainly utilizing internal information such as topics or phrases/words, which often suffer from an inability to comprehensively mine the text semantics, limiting the reciprocal guidance between network structure and text semantics. To address these problems, we propose a novel text-rich graph neural network with external knowledge (TeKo), in order to take full advantage of both structural and textual information within text-rich networks. Specifically, we first present a flexible heterogeneous semantic network that incorporates high-quality entities and interactions among documents and entities. We then introduce two types of external knowledge, that is, structured triplets and unstructured entity description, to gain a deeper insight into textual semantics. We further design a reciprocal convolutional mechanism for the constructed heterogeneous semantic network, enabling network structure and textual semantics to collaboratively enhance each other and learn high-level network representations. Extensive experimental results on four public text-rich networks as well as a large-scale e-commerce searching dataset illustrate the superior performance of TeKo over state-of-the-art baselines.