用JS散度捕捉文本图中的结构与上下文差异，提升表示学习效果
Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning
- 基于JS散度建模节点间结构与文本的相似性与差异性
- 在多个数据集上超越现有基线模型，提升表示质量
- 适合处理含丰富文本的复杂图结构数据的任务
本文研究了富文本图中普遍存在的上下文与结构差异对表示学习的影响。为此，提出一种新的学习范式——Jensen-Shannon散度消息传递（JSDMP），不仅考虑结构与文本的相似性，还通过JS散度捕捉其差异性，联合用于计算文本节点间的消息权重，使表示能从真正相关的文本节点中学习上下文与结构信息。基于JSDMP，设计两种新型图神经网络：分歧消息传递图卷积网络（DMPGCN）和分歧消息传递Page-Rank图神经网络（DMPPRG）。二者在多个标准富文本数据集上进行了广泛测试，并与多种先进基线方法对比。实验结果表明，两者均显著优于现有方法，验证了所提范式的有效性。
原文摘要 · Abstract (English)
In this paper, we investigate how the widely existing contextual and structural divergence may influence the representation learning in rich-text graphs. To this end, we propose Jensen-Shannon Divergence Message-Passing (JSDMP), a new learning paradigm for rich-text graph representation learning. Besides considering similarity regarding structure and text, JSDMP further captures their corresponding dissimilarity by Jensen-Shannon divergence. Similarity and dissimilarity are then jointly used to compute new message weights among text nodes, thus enabling representations to learn with contextual and structural information from truly correlated text nodes. With JSDMP, we propose two novel graph neural networks, namely Divergent message-passing graph convolutional network (DMPGCN) and Divergent message-passing Page-Rank graph neural networks (DMPPRG), for learning representations in rich-text graphs. DMPGCN and DMPPRG have been extensively texted on well-established rich-text datasets and compared with several state-of-the-art baselines. The experimental results show that DMPGCN and DMPPRG can outperform other baselines, demonstrating the effectiveness of the proposed Jensen-Shannon Divergence Message-Passing paradigm
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。