# HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification

arXiv: https://arxiv.org/abs/2008.12842 · HTML: https://mlsanity.com/paper/2008.12842/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

## Built on by (most cited first, 21 of 21)

- [HiGPT: Heterogeneous Graph Language Model](https://mlsanity.com/paper/2402.16024/) (2024)
- [Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP](https://mlsanity.com/paper/2109.03777/) (2021)
- [Instance-Dependent Noisy Label Learning via Graphical Modelling](https://mlsanity.com/paper/2209.00906/) (2022)
- [Graph Neural Networks for Text Classification: A Survey](https://mlsanity.com/paper/2304.11534/) (2023)
- [Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification](https://mlsanity.com/paper/2111.00180/) (2021)
- [ME-GCN: Multi-dimensional Edge-Embedded Graph Convolutional Networks for Semi-supervised Text Classification](https://mlsanity.com/paper/2204.04618/) (2022)
- [Analysis of Convolutions, Non-linearity and Depth in Graph Neural Networks using Neural Tangent Kernel](https://mlsanity.com/paper/2210.09809/) (2022)
- [Inductive Graph Transformer for Delivery Time Estimation](https://mlsanity.com/paper/2211.02863/) (2022)
- [Investigating the Interplay between Features and Structures in Graph Learning](https://mlsanity.com/paper/2308.09570/) (2023)
- [LiGCN: Label-interpretable Graph Convolutional Networks for Multi-label Text Classification](https://mlsanity.com/paper/2103.14620/) (2021)
- [BioIE: Biomedical Information Extraction with Multi-head Attention Enhanced Graph Convolutional Network](https://mlsanity.com/paper/2110.13683/) (2021)
- [GLAM: Graph Learning by Modeling Affinity to Labeled Nodes for Graph Neural Networks](https://mlsanity.com/paper/2102.10403/) (2021)
- [Improving Graph-Based Text Representations with Character and Word Level N-grams](https://mlsanity.com/paper/2210.05999/) (2022)
- [User Embedding based Neighborhood Aggregation Method for Inductive Recommendation](https://mlsanity.com/paper/2102.07575/) (2021)
- [Are We Really Making Much Progress in Text Classification? A Comparative Review](https://mlsanity.com/paper/2204.03954/) (2022)
- [Text Classification using Graph Convolutional Networks: A Comprehensive Survey](https://mlsanity.com/paper/2410.09399/) (2024)
- [Revisiting SVD to generate powerful Node Embeddings for Recommendation Systems](https://mlsanity.com/paper/2110.03665/) (2021)
- [Text Representation Enrichment Utilizing Graph based Approaches: Stock Market Technical Analysis Case Study](https://mlsanity.com/paper/2211.16103/) (2022)
- [Relational Graph Convolutional Networks for Sentiment Analysis](https://mlsanity.com/paper/2404.13079/) (2024)
- [Graph Neural Networks on Discriminative Graphs of Words](https://mlsanity.com/paper/2410.20469/) (2024)
- [ModTGCN: Modularity-aware Graph Neural Networks for Text Classification](https://mlsanity.com/paper/2606.23694/) (2026)

## Abstract (arXiv)

We consider the problem of learning efficient and inductive graph convolutional networks for text classification with a large number of examples and features. Existing state-of-the-art graph embedding based methods such as predictive text embedding (PTE) and TextGCN have shortcomings in terms of predictive performance, scalability and inductive capability. To address these limitations, we propose a heterogeneous graph convolutional network (HeteGCN) modeling approach that unites the best aspects of PTE and TextGCN together. The main idea is to learn feature embeddings and derive document embeddings using a HeteGCN architecture with different graphs used across layers. We simplify TextGCN by dissecting into several HeteGCN models which (a) helps to study the usefulness of individual models and (b) offers flexibility in fusing learned embeddings from different models. In effect, the number of model parameters is reduced significantly, enabling faster training and improving performance in small labeled training set scenario. Our detailed experimental studies demonstrate the efficacy of the proposed approach.