# Information Fusion: Scaling Subspace-Driven Approaches

arXiv: https://arxiv.org/abs/2204.12035 · HTML: https://mlsanity.com/paper/2204.12035/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 43 references that are in the map.
- First posted on arXiv 26 Apr 2022.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Subspace Clustering Networks](https://mlsanity.com/paper/1709.02508/) (2017)
- [Deep Multimodal Subspace Clustering Networks](https://mlsanity.com/paper/1804.06498/) (2018)
- [Multi-view Deep Subspace Clustering Networks](https://mlsanity.com/paper/1908.01978/) (2019)
- [Clustering on Multi-Layer Graphs via Subspace Analysis on Grassmann Manifolds](https://mlsanity.com/paper/1303.2221/) (2013)
- [Cross-Modality Distillation: A case for Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1807.07682/) (2018)
- [Multilayer Spectral Graph Clustering via Convex Layer Aggregation: Theory and Algorithms](https://mlsanity.com/paper/1708.02620/) (2017)
- [Robust Group Subspace Recovery: A New Approach for Multi-Modality Data Fusion](https://mlsanity.com/paper/2006.10657/) (2020)
- [Enhanced detectability of community structure in multilayer networks through layer aggregation](https://mlsanity.com/paper/1511.05271/) (2015)
- [Decision Level Fusion: An Event Driven Approach](https://mlsanity.com/paper/1809.09166/) (2018)
- [Latent Code-Based Fusion: A Volterra Neural Network Approach](https://mlsanity.com/paper/2104.04829/) (2021)

## Abstract (arXiv)

In this work, we seek to exploit the deep structure of multi-modal data to robustly exploit the group subspace distribution of the information using the Convolutional Neural Network (CNN) formalism. Upon unfolding the set of subspaces constituting each data modality, and learning their corresponding encoders, an optimized integration of the generated inherent information is carried out to yield a characterization of various classes. Referred to as deep Multimodal Robust Group Subspace Clustering (DRoGSuRe), this approach is compared against the independently developed state-of-the-art approach named Deep Multimodal Subspace Clustering (DMSC). Experiments on different multimodal datasets show that our approach is competitive and more robust in the presence of noise.