# Towards Consistency and Complementarity: A Multiview Graph Information Bottleneck Approach

arXiv: https://arxiv.org/abs/2210.05676 · HTML: https://mlsanity.com/paper/2210.05676/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 11 Oct 2022.

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [Graph Neural Networks for Social Recommendation](https://mlsanity.com/paper/1902.07243/) (2019)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [On Variational Bounds of Mutual Information](https://mlsanity.com/paper/1905.06922/) (2019)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [AM-GCN: Adaptive Multi-channel Graph Convolutional Networks](https://mlsanity.com/paper/2007.02265/) (2020)
- [Graph Information Bottleneck for Subgraph Recognition](https://mlsanity.com/paper/2010.05563/) (2020)
- [Unsupervised Attributed Multiplex Network Embedding](https://mlsanity.com/paper/1911.06750/) (2019)
- [HDMI: High-order Deep Multiplex Infomax](https://mlsanity.com/paper/2102.07810/) (2021)
- [Graph Structure Learning with Variational Information Bottleneck](https://mlsanity.com/paper/2112.08903/) (2021)
- [Event-based Motion Segmentation with Spatio-Temporal Graph Cuts](https://mlsanity.com/paper/2012.08730/) (2020)
- [Graph Auto-Encoder Via Neighborhood Wasserstein Reconstruction](https://mlsanity.com/paper/2202.09025/) (2022)
- [LatentGNN: Learning Efficient Non-local Relations for Visual Recognition](https://mlsanity.com/paper/1905.11634/) (2019)

## Abstract (arXiv)

The empirical studies of Graph Neural Networks (GNNs) broadly take the original node feature and adjacency relationship as singleview input, ignoring the rich information of multiple graph views. To circumvent this issue, the multiview graph analysis framework has been developed to fuse graph information across views. How to model and integrate shared (i.e. consistency) and view-specific (i.e. complementarity) information is a key issue in multiview graph analysis. In this paper, we propose a novel Multiview Variational Graph Information Bottleneck (MVGIB) principle to maximize the agreement for common representations and the disagreement for view-specific representations. Under this principle, we formulate the common and view-specific information bottleneck objectives across multiviews by using constraints from mutual information. However, these objectives are hard to directly optimize since the mutual information is computationally intractable. To tackle this challenge, we derive variational lower and upper bounds of mutual information terms, and then instead optimize variational bounds to find the approximate solutions for the information objectives. Extensive experiments on graph benchmark datasets demonstrate the superior effectiveness of the proposed method.