# Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations

arXiv: https://arxiv.org/abs/1901.06965 · HTML: https://mlsanity.com/paper/1901.06965/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2019.

## Built on by (most cited first, 13 of 13)

- [Self-Supervised Learning of Graph Neural Networks: A Unified Review](https://mlsanity.com/paper/2102.10757/) (2021)
- [Interpreting and Unifying Graph Neural Networks with An Optimization Framework](https://mlsanity.com/paper/2101.11859/) (2021)
- [Graph Pooling for Graph Neural Networks: Progress, Challenges, and Opportunities](https://mlsanity.com/paper/2204.07321/) (2022)
- [Optimization-Induced Graph Implicit Nonlinear Diffusion](https://mlsanity.com/paper/2206.14418/) (2022)
- [Discourse-level Relation Extraction via Graph Pooling](https://mlsanity.com/paper/2101.00124/) (2021)
- [Curvature-based Pooling within Graph Neural Networks](https://mlsanity.com/paper/2308.16516/) (2023)
- [ViCGCN: Graph Convolutional Network with Contextualized Language Models for Social Media Mining in Vietnamese](https://mlsanity.com/paper/2309.02902/) (2023)
- [BioX-CPath: Biologically-driven Explainable Diagnostics for Multistain IHC Computational Pathology](https://mlsanity.com/paper/2503.20880/) (2025)
- [Net-Ev2: A Generative Simulator for Network Event Evolution](https://mlsanity.com/paper/2606.12494/) (2026)
- [Hierarchical Aspect-guided Explanation Generation for Explainable Recommendation](https://mlsanity.com/paper/2110.10358/) (2021)
- [MUSTANG: Multi-Stain Self-Attention Graph Multiple Instance Learning Pipeline for Histopathology Whole Slide Images](https://mlsanity.com/paper/2309.10650/) (2023)
- [LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisation](https://mlsanity.com/paper/2504.08530/) (2025)
- [S2-UniSeg: Fast Universal Agglomerative Pooling for Scalable Segment Anything without Supervision](https://mlsanity.com/paper/2508.06995/) (2025)

## Abstract (arXiv)

With the development of graph convolutional networks (GCN), deep learning methods have started to be used on graph data. In additional to convolutional layers, pooling layers are another important components of deep learning. However, no effective pooling methods have been developed for graphs currently. In this work, we propose the graph pooling (gPool) layer, which employs a trainable projection vector to measure the importance of nodes in graphs. By selecting the k-most important nodes to form the new graph, gPool achieves the same objective as regular max pooling layers operating on images. Another limitation of GCN when used on graph-based text representation tasks is that, GCNs do not consider the order information of nodes in graph. To address this limitation, we propose the hybrid convolutional (hConv) layer that combines GCN and regular convolutional operations. The hConv layer is capable of increasing receptive fields quickly and computing features automatically. Based on the proposed gPool and hConv layers, we develop new deep networks for text categorization tasks. Our results show that the networks based on gPool and hConv layers achieves new state-of-the-art performance as compared to baseline methods.