# Latent Code-Based Fusion: A Volterra Neural Network Approach

arXiv: https://arxiv.org/abs/2104.04829 · HTML: https://mlsanity.com/paper/2104.04829/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 29 references that are in the map.
- First posted on arXiv 10 Apr 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Non-linear Convolution Filters for CNN-based Learning](https://mlsanity.com/paper/1708.07038/) (2017)
- [Deep Multimodal Subspace Clustering Networks](https://mlsanity.com/paper/1804.06498/) (2018)
- [Cross-Modality Distillation: A case for Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1807.07682/) (2018)
- [Volterra Neural Networks (VNNs)](https://mlsanity.com/paper/1910.09616/) (2019)
- [Robust Group Subspace Recovery: A New Approach for Multi-Modality Data Fusion](https://mlsanity.com/paper/2006.10657/) (2020)
- [Decision Level Fusion: An Event Driven Approach](https://mlsanity.com/paper/1809.09166/) (2018)

## Built on by (most cited first, 2 of 2)

- [Information Fusion: Scaling Subspace-Driven Approaches](https://mlsanity.com/paper/2204.12035/) (2022)
- [KVNN: Learnable Multi-Kernel Volterra Neural Networks](https://mlsanity.com/paper/2604.15141/) (2026)

## Abstract (arXiv)

We propose a deep structure encoder using the recently introduced Volterra Neural Networks (VNNs) to seek a latent representation of multi-modal data whose features are jointly captured by a union of subspaces. The so-called self-representation embedding of the latent codes leads to a simplified fusion which is driven by a similarly constructed decoding. The Volterra Filter architecture achieved reduction in parameter complexity is primarily due to controlled non-linearities being introduced by the higher-order convolutions in contrast to generalized activation functions. Experimental results on two different datasets have shown a significant improvement in the clustering performance for VNNs auto-encoder over conventional Convolutional Neural Networks (CNNs) auto-encoder. In addition, we also show that the proposed approach demonstrates a much-improved sample complexity over CNN-based auto-encoder with a superb robust classification performance.