# Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks

arXiv: https://arxiv.org/abs/2102.11479 · HTML: https://mlsanity.com/paper/2102.11479/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Adversarial Training Methods for Semi-Supervised Text Classification](https://mlsanity.com/paper/1605.07725/) (2016)
- [Contextual Augmentation: Data Augmentation by Words with Paradigmatic Relations](https://mlsanity.com/paper/1805.06201/) (2018)
- [Scaling Graph Neural Networks with Approximate PageRank](https://mlsanity.com/paper/2007.01570/) (2020)
- [Learning to Self-Train for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1906.00562/) (2019)
- [Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks](https://mlsanity.com/paper/2004.13826/) (2020)
- [Automated Phrase Mining from Massive Text Corpora](https://mlsanity.com/paper/1702.04457/) (2017)
- [Weakly-Supervised Neural Text Classification](https://mlsanity.com/paper/1809.01478/) (2018)
- [Large-Scale Training System for 100-Million Classification at Alibaba](https://mlsanity.com/paper/2102.06025/) (2021)
- [Minimally Supervised Categorization of Text with Metadata](https://mlsanity.com/paper/2005.00624/) (2020)
- [Improved Semantic-Aware Network Embedding with Fine-Grained Word Alignment](https://mlsanity.com/paper/1808.09633/) (2018)

## Built on by (most cited first, 11 of 11)

- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [Can we Soft Prompt LLMs for Graph Learning Tasks?](https://mlsanity.com/paper/2402.10359/) (2024)
- [GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs](https://mlsanity.com/paper/2310.15109/) (2023)
- [Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks](https://mlsanity.com/paper/2205.10282/) (2022)
- [Metadata-Induced Contrastive Learning for Zero-Shot Multi-Label Text Classification](https://mlsanity.com/paper/2202.05932/) (2022)
- [MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information](https://mlsanity.com/paper/2111.04022/) (2021)
- [KGTrust: Evaluating Trustworthiness of SIoT via Knowledge Enhanced Graph Neural Networks](https://mlsanity.com/paper/2302.11396/) (2023)
- [Minimally Supervised Learning using Topological Projections in Self-Organizing Maps](https://mlsanity.com/paper/2401.06923/) (2024)
- [TeKo: Text-Rich Graph Neural Networks with External Knowledge](https://mlsanity.com/paper/2206.07253/) (2022)
- [Can Large Language Models Act as Ensembler for Multi-GNNs?](https://mlsanity.com/paper/2410.16822/) (2024)
- [Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning](https://mlsanity.com/paper/2603.12290/) (2026)

## Abstract (arXiv)

Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting that aims to categorize documents effectively, with a couple of seed documents annotated per category. We recognize that texts collected from the Web are often structure-rich, i.e., accompanied by various metadata. One can easily organize the corpus into a text-rich network, joining raw text documents with document attributes, high-quality phrases, label surface names as nodes, and their associations as edges. Such a network provides a holistic view of the corpus' heterogeneous data sources and enables a joint optimization for network-based analysis and deep textual model training. We therefore propose a novel framework for minimally supervised categorization by learning from the text-rich network. Specifically, we jointly train two modules with different inductive biases -- a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning. Each module generates pseudo training labels from the unlabeled document set, and both modules mutually enhance each other by co-training using pooled pseudo labels. We test our model on two real-world datasets. On the challenging e-commerce product categorization dataset with 683 categories, our experiments show that given only three seed documents per category, our framework can achieve an accuracy of about 92%, significantly outperforming all compared methods; our accuracy is only less than 2% away from the supervised BERT model trained on about 50K labeled documents.