# Synchronous Multi-view Neural Diffusion

arXiv: https://arxiv.org/abs/2609.39019 · HTML: https://mlsanity.com/paper/2609.39019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 52 references that are in the map.
- First posted on arXiv 30 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [Diffusion Improves Graph Learning](https://mlsanity.com/paper/1911.05485/) (2019)
- [PDE-Net: Learning PDEs from Data](https://mlsanity.com/paper/1710.09668/) (2017)
- [Diffusion-Convolutional Neural Networks](https://mlsanity.com/paper/1511.02136/) (2015)
- [A Survey on Multi-view Learning](https://mlsanity.com/paper/1304.5634/) (2013)
- [Implicit Graph Neural Networks](https://mlsanity.com/paper/2009.06211/) (2020)
- [Unsupervised Attributed Multiplex Network Embedding](https://mlsanity.com/paper/1911.06750/) (2019)
- [Trusted Unified Feature-Neighborhood Dynamics for Multi-View Classification](https://mlsanity.com/paper/2409.00755/) (2024)
- [Deep Gaussian Markov Random Fields](https://mlsanity.com/paper/2002.07467/) (2020)
- [Semi-Supervised Deep Learning for Multiplex Networks](https://mlsanity.com/paper/2110.02038/) (2021)
- [Attributed Multi-order Graph Convolutional Network for Heterogeneous Graphs](https://mlsanity.com/paper/2304.06336/) (2023)
- [Implicit Graph Neural Diffusion Networks: Convergence, Generalization, and Over-Smoothing](https://mlsanity.com/paper/2308.03306/) (2023)

## Abstract (arXiv)

Multi-view learning seeks to learn more comprehensive representations by exploiting the complementarity and consistency across diverse modalities or views. However, existing multi-view fusion strategies treat intra- and inter-view fusion as independent stages, without simultaneously considering the evolution within views and the dependency across views. Such an asynchronous fusion paradigm inevitably constrains cross-view interactions due to conflicting view-specific structural inductive biases. As a result, information flow is prone to distortion and compression along intermediate pathways, confining the model to learn within a restricted solution space. To address this, we propose Synchronous Multi-view Neural Diffusion (SynMDiff), which conceptualizes the multi-view feature space as a unified dynamical system driven by a diffusion process. By modeling the diffusion flow across arbitrary dyadic feature interactions in a joint space, SynMDiff enables the concurrent and adaptive intra- and inter-view information fusion. While a direct implementation of this synchronized mechanism incurs prohibitive computational costs, we further introduce an energy-based topological sampling strategy and an Ego-Net style centralized training architecture, ensuring both efficiency and scalability during learning and inference. Due to its conceptual elegance and computational efficacy, evaluations on real-world datasets demonstrate that SynMDiff outperforms the baselines by a large margin.