# Deep Convolutional Networks on Graph-Structured Data

arXiv: https://arxiv.org/abs/1506.05163 · HTML: https://mlsanity.com/paper/1506.05163/

## Key facts

- Cited by 246 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jun 2015.

## Built on by (most cited first, 30 of 246)

- [GRAND: Graph Neural Diffusion](https://mlsanity.com/paper/2106.10934/) (2021)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning](https://mlsanity.com/paper/2103.00113/) (2021)
- [Training Graph Neural Networks with 1000 Layers](https://mlsanity.com/paper/2106.07476/) (2021)
- [Graph Learning: A Survey](https://mlsanity.com/paper/2105.00696/) (2021)
- [Hyperbolic Deep Neural Networks: A Survey](https://mlsanity.com/paper/2101.04562/) (2021)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision](https://mlsanity.com/paper/2204.04879/) (2022)
- [TPCN: Temporal Point Cloud Networks for Motion Forecasting](https://mlsanity.com/paper/2103.03067/) (2021)
- [Graph Mamba: Towards Learning on Graphs with State Space Models](https://mlsanity.com/paper/2402.08678/) (2024)
- [Beltrami Flow and Neural Diffusion on Graphs](https://mlsanity.com/paper/2110.09443/) (2021)
- [NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs](https://mlsanity.com/paper/2106.04714/) (2021)
- [Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels](https://mlsanity.com/paper/2201.00232/) (2022)
- [Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics](https://mlsanity.com/paper/2105.03703/) (2021)
- [A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective](https://mlsanity.com/paper/2209.13232/) (2022)
- [Graph Few-shot Class-incremental Learning](https://mlsanity.com/paper/2112.12819/) (2021)
- [Sampling methods for efficient training of graph convolutional networks: A survey](https://mlsanity.com/paper/2103.05872/) (2021)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)
- [Autobahn: Automorphism-based Graph Neural Nets](https://mlsanity.com/paper/2103.01710/) (2021)
- [p-Laplacian Based Graph Neural Networks](https://mlsanity.com/paper/2111.07337/) (2021)
- [FMP: Toward Fair Graph Message Passing against Topology Bias](https://mlsanity.com/paper/2202.04187/) (2022)
- [SAM-Assisted Remote Sensing Imagery Semantic Segmentation with Object and Boundary Constraints](https://mlsanity.com/paper/2312.02464/) (2023)
- [FedGL: Federated Graph Learning Framework with Global Self-Supervision](https://mlsanity.com/paper/2105.03170/) (2021)
- [RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2110.14223/) (2021)
- [PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving](https://mlsanity.com/paper/2311.08100/) (2023)
- [Network of Tensor Time Series](https://mlsanity.com/paper/2102.07736/) (2021)
- [Graph Lifelong Learning: A Survey](https://mlsanity.com/paper/2202.10688/) (2022)
- [DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks](https://mlsanity.com/paper/2303.02448/) (2023)
- [Learning Conjoint Attentions for Graph Neural Nets](https://mlsanity.com/paper/2102.03147/) (2021)

## Abstract (arXiv)

Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions. However, there exist other important examples, such as text documents or bioinformatic data, that may lack some or all of these strong statistical regularities. In this paper we consider the general question of how to construct deep architectures with small learning complexity on general non-Euclidean domains, which are typically unknown and need to be estimated from the data. In particular, we develop an extension of Spectral Networks which incorporates a Graph Estimation procedure, that we test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.