# Learning Graph Representations with Embedding Propagation

arXiv: https://arxiv.org/abs/1710.03059 · HTML: https://mlsanity.com/paper/1710.03059/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2017.

## Built on by (most cited first, 30 of 38)

- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [GraphMAE: Self-Supervised Masked Graph Autoencoders](https://mlsanity.com/paper/2205.10803/) (2022)
- [Large-Scale Representation Learning on Graphs via Bootstrapping](https://mlsanity.com/paper/2102.06514/) (2021)
- [Self-supervised Graph-level Representation Learning with Local and Global Structure](https://mlsanity.com/paper/2106.04113/) (2021)
- [Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling](https://mlsanity.com/paper/2304.02806/) (2023)
- [Local Augmentation for Graph Neural Networks](https://mlsanity.com/paper/2109.03856/) (2021)
- [Heterogeneous Graph Masked Autoencoders](https://mlsanity.com/paper/2208.09957/) (2022)
- [SDGNN: Learning Node Representation for Signed Directed Networks](https://mlsanity.com/paper/2101.02390/) (2021)
- [Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN](https://mlsanity.com/paper/2207.00012/) (2022)
- [Dynamic-Group-Aware Networks for Multi-Agent Trajectory Prediction with Relational Reasoning](https://mlsanity.com/paper/2206.13114/) (2022)
- [Fair Node Representation Learning via Adaptive Data Augmentation](https://mlsanity.com/paper/2201.08549/) (2022)
- [Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective](https://mlsanity.com/paper/2107.01475/) (2021)
- [SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Masking](https://mlsanity.com/paper/2301.12458/) (2023)
- [Predicting Patient Outcomes with Graph Representation Learning](https://mlsanity.com/paper/2101.03940/) (2021)
- [TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs](https://mlsanity.com/paper/2112.02052/) (2021)
- [MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms](https://mlsanity.com/paper/2209.06800/) (2022)
- [Fairness-Aware Node Representation Learning](https://mlsanity.com/paper/2106.05391/) (2021)
- [Learning Graph Augmentations to Learn Graph Representations](https://mlsanity.com/paper/2201.09830/) (2022)
- [Graph Contrastive Learning with Personalized Augmentation](https://mlsanity.com/paper/2209.06560/) (2022)
- [FairGAT: Fairness-aware Graph Attention Networks](https://mlsanity.com/paper/2303.14591/) (2023)
- [BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices](https://mlsanity.com/paper/2104.06214/) (2021)
- [Geometric Graph Representation Learning via Maximizing Rate Reduction](https://mlsanity.com/paper/2202.06241/) (2022)
- [Communication-Efficient Sampling for Distributed Training of Graph Convolutional Networks](https://mlsanity.com/paper/2101.07706/) (2021)
- [GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processing](https://mlsanity.com/paper/2111.00680/) (2021)
- [Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning](https://mlsanity.com/paper/2205.15746/) (2022)
- [Computing Graph Descriptors on Edge Streams](https://mlsanity.com/paper/2109.01494/) (2021)
- [Toward Enhanced Robustness in Unsupervised Graph Representation Learning: A Graph Information Bottleneck Perspective](https://mlsanity.com/paper/2201.08557/) (2022)
- [PiPAD: Pipelined and Parallel Dynamic GNN Training on GPUs](https://mlsanity.com/paper/2301.00391/) (2023)
- [A Contrastive Variational Graph Auto-Encoder for Node Clustering](https://mlsanity.com/paper/2312.16830/) (2023)
- [Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning](https://mlsanity.com/paper/2104.01711/) (2021)

## Abstract (arXiv)

We propose Embedding Propagation (EP), an unsupervised learning framework for graph-structured data. EP learns vector representations of graphs by passing two types of messages between neighboring nodes. Forward messages consist of label representations such as representations of words and other attributes associated with the nodes. Backward messages consist of gradients that result from aggregating the label representations and applying a reconstruction loss. Node representations are finally computed from the representation of their labels. With significantly fewer parameters and hyperparameters an instance of EP is competitive with and often outperforms state of the art unsupervised and semi-supervised learning methods on a range of benchmark data sets.