# Initialization for Network Embedding: A Graph Partition Approach

arXiv: https://arxiv.org/abs/1908.10697 · HTML: https://mlsanity.com/paper/1908.10697/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2019.

## Built on by (most cited first, 8 of 8)

- [MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution](https://mlsanity.com/paper/2208.07012/) (2022)
- [Predicting the Silent Majority on Graphs: Knowledge Transferable Graph Neural Network](https://mlsanity.com/paper/2302.00873/) (2023)
- [Bridged-GNN: Knowledge Bridge Learning for Effective Knowledge Transfer](https://mlsanity.com/paper/2308.09499/) (2023)
- [Large-Scale Network Embedding in Apache Spark](https://mlsanity.com/paper/2106.10620/) (2021)
- [Link Prediction with Untrained Message Passing Layers](https://mlsanity.com/paper/2406.16687/) (2024)
- [FROG: Effective Friend Recommendation in Online Games via Modality-aware User Preferences](https://mlsanity.com/paper/2504.09428/) (2025)
- [Heterogeneous Influence Maximization in User Recommendation](https://mlsanity.com/paper/2508.13517/) (2025)
- [Learning node embeddings via summary graphs: a brief theoretical analysis](https://mlsanity.com/paper/2207.01189/) (2022)

## Abstract (arXiv)

Network embedding has been intensively studied in the literature and widely used in various applications, such as link prediction and node classification. While previous work focus on the design of new algorithms or are tailored for various problem settings, the discussion of initialization strategies in the learning process is often missed. In this work, we address this important issue of initialization for network embedding that could dramatically improve the performance of the algorithms on both effectiveness and efficiency. Specifically, we first exploit the graph partition technique that divides the graph into several disjoint subsets, and then construct an abstract graph based on the partitions. We obtain the initialization of the embedding for each node in the graph by computing the network embedding on the abstract graph, which is much smaller than the input graph, and then propagating the embedding among the nodes in the input graph. With extensive experiments on various datasets, we demonstrate that our initialization technique significantly improves the performance of the state-of-the-art algorithms on the evaluations of link prediction and node classification by up to 7.76% and 8.74% respectively. Besides, we show that the technique of initialization reduces the running time of the state-of-the-arts by at least 20%.