# Learnable Graph Convolutional Network and Feature Fusion for Multi-view Learning

arXiv: https://arxiv.org/abs/2211.09155 · HTML: https://mlsanity.com/paper/2211.09155/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 58 references that are in the map.
- First posted on arXiv 16 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Beyond Low-frequency Information in Graph Convolutional Networks](https://mlsanity.com/paper/2101.00797/) (2021)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [AM-GCN: Adaptive Multi-channel Graph Convolutional Networks](https://mlsanity.com/paper/2007.02265/) (2020)
- [Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels](https://mlsanity.com/paper/1902.11038/) (2019)
- [A Survey of Multi-View Representation Learning](https://mlsanity.com/paper/1610.01206/) (2016)
- [Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification](https://mlsanity.com/paper/1904.04238/) (2019)
- [Multi-view Laplacian Support Vector Machines](https://mlsanity.com/paper/1307.7024/) (2013)
- [2D-3D Geometric Fusion Network using Multi-Neighbourhood Graph Convolution for RGB-D Indoor Scene Classification](https://mlsanity.com/paper/2009.11154/) (2020)
- [Relation Regularized Scene Graph Generation](https://mlsanity.com/paper/2202.10826/) (2022)

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

- [AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing](https://mlsanity.com/paper/2304.07014/) (2023)
- [RSEA-MVGNN: Multi-View Graph Neural Network with Reliable Structural Enhancement and Aggregation](https://mlsanity.com/paper/2408.07331/) (2024)
- [Beyond Graph Convolutional Network: An Interpretable Regularizer-centered Optimization Framework](https://mlsanity.com/paper/2301.04318/) (2023)
- [Deep Graph-Level Clustering Using Pseudo-Label-Guided Mutual Information Maximization Network](https://mlsanity.com/paper/2302.02369/) (2023)
- [Attributed Multi-order Graph Convolutional Network for Heterogeneous Graphs](https://mlsanity.com/paper/2304.06336/) (2023)
- [Graph Representation Learning for Infrared and Visible Image Fusion](https://mlsanity.com/paper/2311.00291/) (2023)
- [Multi-view Graph Convolutional Networks with Differentiable Node Selection](https://mlsanity.com/paper/2212.05124/) (2022)
- [A Semantic-Aware and Multi-Guided Network for Infrared-Visible Image Fusion](https://mlsanity.com/paper/2407.06159/) (2024)
- [A Re-node Self-training Approach for Deep Graph-based Semi-supervised Classification on Multi-view Image Data](https://mlsanity.com/paper/2510.24791/) (2025)
- [Efficient Time Series Clustering from Multiscale Reservoir Dynamics with Granular-Ball Anchoring Graph Optimization](https://mlsanity.com/paper/2606.12077/) (2026)
- [Unity in Diversity: Multi-expert Knowledge Confrontation and Collaboration for Generalizable Vehicle Re-identification](https://mlsanity.com/paper/2407.07351/) (2024)
- [Multi-agent Auditory Scene Analysis](https://mlsanity.com/paper/2507.02755/) (2025)
- [Multi-view Graph Convolutional Network with Fully Leveraging Consistency via Granular-ball-based Topology Construction, Feature Enhancement and Interactive Fusion](https://mlsanity.com/paper/2603.26729/) (2026)

## Abstract (arXiv)

In practical applications, multi-view data depicting objectives from assorted perspectives can facilitate the accuracy increase of learning algorithms. However, given multi-view data, there is limited work for learning discriminative node relationships and graph information simultaneously via graph convolutional network that has drawn the attention from considerable researchers in recent years. Most of existing methods only consider the weighted sum of adjacency matrices, yet a joint neural network of both feature and graph fusion is still under-explored. To cope with these issues, this paper proposes a joint deep learning framework called Learnable Graph Convolutional Network and Feature Fusion (LGCN-FF), consisting of two stages: feature fusion network and learnable graph convolutional network. The former aims to learn an underlying feature representation from heterogeneous views, while the latter explores a more discriminative graph fusion via learnable weights and a parametric activation function dubbed Differentiable Shrinkage Activation (DSA) function. The proposed LGCN-FF is validated to be superior to various state-of-the-art methods in multi-view semi-supervised classification.