# Deep Feature Learning for Graphs

arXiv: https://arxiv.org/abs/1704.08829 · HTML: https://mlsanity.com/paper/1704.08829/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2017.

## Built on by (most cited first, 6 of 6)

- [Personalized Audiobook Recommendations at Spotify Through Graph Neural Networks](https://mlsanity.com/paper/2403.05185/) (2024)
- [Graph Learning with Localized Neighborhood Fairness](https://mlsanity.com/paper/2212.12040/) (2022)
- [A Hypergraph Neural Network Framework for Learning Hyperedge-Dependent Node Embeddings](https://mlsanity.com/paper/2212.14077/) (2022)
- [Noise-robust classification with hypergraph neural network](https://mlsanity.com/paper/2102.01934/) (2021)
- [A Brief Survey on Representation Learning based Graph Dimensionality Reduction Techniques](https://mlsanity.com/paper/2211.05594/) (2022)
- [PropEnc: A Property Encoder for Graph Neural Networks](https://mlsanity.com/paper/2409.11554/) (2024)

## Abstract (arXiv)

This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs. In particular, DeepGL begins by deriving a set of base features (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the output from the previous layer to learn features of a higher-order. Contrary to previous work, DeepGL learns relational functions (each representing a feature) that generalize across-networks and therefore useful for graph-based transfer learning tasks. Moreover, DeepGL naturally supports attributed graphs, learns interpretable features, and is space-efficient (by learning sparse feature vectors). In addition, DeepGL is expressive, flexible with many interchangeable components, efficient with a time complexity of O(|E|), and scalable for large networks via an efficient parallel implementation. Compared with the state-of-the-art method, DeepGL is (1) effective for across-network transfer learning tasks and attributed graph representation learning, (2) space-efficient requiring up to 6x less memory, (3) fast with up to 182x speedup in runtime performance, and (4) accurate with an average improvement of 20% or more on many learning tasks.