Inferring Graph Signal Translations as Invariant Transformations for Classification Tasks
Not on the map. Why?
Abstract (arXiv)
The field of Graph Signal Processing (GSP) has proposed tools to generalize harmonic analysis to complex domains represented through graphs. Among these tools are translations, which are required to define many others. Most works propose to define translations using solely the graph structure (i.e. edges). Such a problem is ill-posed in general as a graph conveys information about neighborhood but not about directions. In this paper, we propose to infer translations as edge-constrained operations that make a supervised classification problem invariant using a deep learning framework. As such, our methodology uses both the graph structure and labeled signals to infer translations. We perform experiments with regular 2D images and abstract hyperlink networks to show the effectiveness of the proposed methodology in inferring meaningful translations for signals supported on graphs.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 16 references that are in the map. First posted on arXiv 18 Feb 2021.
Builds on
8 of 16 references.
References · 8
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 826
- 2017Graph Signal Processing: Overview, Challenges and Applicationscited by 413
- 2016Higher-order organization of complex networkscited by 110
- 2016Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1cited by 105
- 2018MotifNet: a motif-based Graph Convolutional Network for directed graphscited by 64
- 2019Attention Based Pruning for Shift Networkscited by 7
- 2017Learning Local Receptive Fields and their Weight Sharing Scheme on Graphscited by 1
Built on by
Not cited yet.