Li Pengyi, Fu Xueying, Chen Juntao, Hu Junyi
Suzhou Yuelan Technology Development Co., Ltd, SuZhou, 215128, China.
School of Computer Sciences, Universiti Sains Malaysia, 11800, Penang, Malaysia.
Sci Rep. 2025 Jan 2;15(1):356. doi: 10.1038/s41598-024-83535-9.
Text Graph Representation Learning through Graph Neural Networks (TG-GNN) is a powerful approach in natural language processing and information retrieval. However, it faces challenges in computational complexity and interpretability. In this work, we propose CoGraphNet, a novel graph-based model for text classification, addressing key issues. To overcome information loss, we construct separate heterogeneous graphs for words and sentences, capturing multi-tiered contextual information. We enhance interpretability by incorporating positional bias weights, improving model clarity. CoGraphNet provides precise analysis, highlighting important words or sentences. We achieve enhanced contextual comprehension and accuracy through novel graph structures and the SwiGLU activation function. Experiments on Ohsumed, MR, R52, and 20NG datasets confirm CoGraphNet's effectiveness in complex classification tasks, demonstrating its superiority.
通过图神经网络的文本图表示学习（TG-GNN）是自然语言处理和信息检索中的一种强大方法。然而，它在计算复杂性和可解释性方面面临挑战。在这项工作中，我们提出了CoGraphNet，一种用于文本分类的新型基于图的模型，解决了关键问题。为了克服信息丢失，我们为单词和句子构建了单独的异构图，捕获多层次的上下文信息。我们通过纳入位置偏差权重来增强可解释性，提高模型清晰度。CoGraphNet提供精确分析，突出重要的单词或句子。我们通过新颖的图结构和SwiGLU激活函数实现了增强的上下文理解和准确性。在Ohsumed、MR、R52和20NG数据集上的实验证实了CoGraphNet在复杂分类任务中的有效性，证明了其优越性。
