Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning
Not on the map. Why?
Abstract (arXiv)
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
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 54 references that are in the map. First posted on arXiv 23 Dec 2025.
Builds on
27 of 54 references.
References · 27
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2017Graph Attention Networkscited by 8,854
- 2017Inductive Representation Learning on Large Graphscited by 6,284
- 2019Simplifying Graph Convolutional Networkscited by 1,470
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,428
- 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
- 2021How Attentive are Graph Attention Networks?cited by 818
- 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
- 2018Graph Convolutional Networks for Text Classificationcited by 345
- 2014Recurrent Neural Network Regularizationcited by 189
15 more
- 2021BertGCN: Transductive Text Classification by Combining GCN and BERTcited by 74
- 2018A Survey on Natural Language Processing for Fake News Detectioncited by 67
- 2019On a generalization of the Jensen-Shannon divergence and the JS-symmetrization of distances relying on abstract meanscited by 61
- 2019Text Level Graph Neural Network for Text Classificationcited by 60
- 2020Tensor Graph Convolutional Networks for Text Classificationcited by 49
- 2020VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classificationcited by 35
- 2021Learning Conjoint Attentions for Graph Neural Netscited by 26
- 2014How Many Topics? Stability Analysis for Topic Modelscited by 16
- 2021Sparse Structure Learning via Graph Neural Networks for Inductive Document Classificationcited by 15
- 2022InducT-GCN: Inductive Graph Convolutional Networks for Text Classificationcited by 15
- 2022ES-GNN: Generalizing Graph Neural Networks Beyond Homophily with Edge Splittingcited by 13
- 2022ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classificationcited by 10
- 2024Road Network Representation Learning with the Third Law of Geographycited by 10
- 2022Not All Neighbors Are Worth Attending to: Graph Selective Attention Networks for Semi-supervised Learningcited by 6
- 2020Relational Thematic Clustering with Mutually Preferred Neighborscited by 5
Built on by
Citing papers per year: 2026: 2.
2 papers.