• Corpus ID: 3591458

MILE: A Multi-Level Framework for Scalable Graph Embedding

@inproceedings{Liang2021MILEAM,
  title={MILE: A Multi-Level Framework for Scalable Graph Embedding},
  author={Jiongqian Liang and Saket Gurukar and Srinivasan Parthasarathy},
  booktitle={ICWSM},
  year={2021}
}
Recently there has been a surge of interest in designing graph embedding methods. Few, if any, can scale to a large-sized graph with millions of nodes due to both computational complexity and memory requirements. In this paper, we relax this limitation by introducing the MultI-Level Embedding (MILE) framework -- a generic methodology allowing contemporary graph embedding methods to scale to large graphs. MILE repeatedly coarsens the graph into smaller ones using a hybrid matching technique to… 

Figures and Tables from this paper

GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding
TLDR
Experiments show that GraphZoom can substantially increase the classification accuracy and significantly accelerate the entire graph embedding process by up to 40.8x, when compared to the state-of-the-art unsupervised embedding methods.
Scalable Robust Graph Embedding with Spark
TLDR
This work proposes a framework for scalable and robust graph embedding based on the MapReduce model, which can distribute any existing embedding technique, and splits a graph into subgraphs to learn their embeddings in isolation and subsequently reconciles the embedding spaces derived for the sub graphs.
LouvainNE: Hierarchical Louvain Method for High Quality and Scalable Network Embedding
TLDR
This paper presents LouvainNE, a hierarchical clustering approach to network embedding that can handle graphs containing tens of billions of edges, as well as its effectiveness in performing downstream network mining tasks such as network reconstruction and node classification.
GOSH: Embedding Big Graphs on Small Hardware
TLDR
Gosh utilizes a novel graph coarsening approach to compress the graph and minimize the work required for embedding, delivering high-quality embeddings at a fraction of the time compared to the state-of-the-art.
Proximity-Based Compression for Network Embedding
TLDR
NECL is a general meta-strategy that improves the efficiency and effectiveness of many state-of-the-art graph embedding algorithms based on node proximity, including DeepWalk, Node2vec, and LINE, and is validated on single and multi-label classification tasks with large real-world graphs.
Initialization for Network Embedding: A Graph Partition Approach
TLDR
This work addresses the important issue of initialization for network embedding that could dramatically improve the performance of the algorithms on both effectiveness and efficiency and demonstrates that the technique of initialization reduces the running time of the state-of-the-arts by at least 20%.
Multi-Level Network Embedding with Boosted Low-Rank Matrix Approximation
  • Jundong Li, Liang Wu, Huan Liu
  • Computer Science
    2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
  • 2019
TLDR
A novel multi-level network embedding framework BoostNE, which can learn multiple node embeddings of different granularity from coarse to fine without imposing the prevalent global low-rank assumption, is proposed.
PyTorch-BigGraph: A Large-scale Graph Embedding System
TLDR
PyTorch-BigGraph (PBG), an embedding system that incorporates several modifications to traditional multi-relation embedding systems that allow it to scale to graphs with billions of nodes and trillions of edges, is presented.
Scaling Up Graph Neural Networks Via Graph Coarsening
TLDR
This paper proposes to use graph coarsening for scalable training of GNNs, which is generic, extremely simple and has sublinear memory and time costs during training and presents extensive theoretical analysis on the effect of using coARSening operations and provides useful guidance on the choice of coarsened methods.
Understanding Coarsening for Embedding Large-Scale Graphs
TLDR
The experiments with a state-of-the-art, fast graph embedding tool show that there is an interplay between the coarsening decisions taken and the embedding quality, and the cost of embedding significantly decreases when coarsened is employed.
...
...

References

SHOWING 1-10 OF 47 REFERENCES
PyTorch-BigGraph: A Large-scale Graph Embedding System
TLDR
PyTorch-BigGraph (PBG), an embedding system that incorporates several modifications to traditional multi-relation embedding systems that allow it to scale to graphs with billions of nodes and trillions of edges, is presented.
Graph Embedding Techniques, Applications, and Performance: A Survey
HARP: Hierarchical Representation Learning for Networks
TLDR
HARP is a general meta-strategy to improve all of the state-of-the-art neural algorithms for embedding graphs, including DeepWalk, LINE, and Node2vec, and it is demonstrated that applying HARP’s hierarchical paradigm yields improved implementations for all three of these methods.
Heterogeneous Network Embedding via Deep Architectures
TLDR
It is demonstrated that the rich content and linkage information in a heterogeneous network can be captured by a multi-resolution deep embedding function, so that similarities among cross-modal data can be measured directly in a common embedding space.
Accelerated Attributed Network Embedding
TLDR
An accelerated attributed network embedding algorithm AANE is proposed, which enables the joint learning process to be done in a distributed manner by decomposing the complex modeling and optimization into many sub-problems.
Fast Network Embedding Enhancement via High Order Proximity Approximation
TLDR
Most existing NRL methods are summarized into a unified two-step framework, including proximity matrix construction and dimension reduction, and Network Embedding Update (NEU) algorithm is proposed which implicitly approximates higher order proximities with theoretical approximation bound.
A Framework for Generalizing Graph-based Representation Learning Methods
TLDR
This work introduces the notion of attributed random walks which serves as a basis for generalizing existing methods such as DeepWalk, node2vec, and many others that leverage random walks and enables these methods to be more widely applicable for both transductive and inductive learning as well as for use on graphs with attributes.
Multi-Layered Network Embedding
TLDR
A principled framework MANE is proposed to model both within-layer connections and cross-layer network dependencies simultaneously in a unified optimization framework for embedding representation learning and experiments on real-world multi-layered networks corroborate the effectiveness of the proposed framework.
Structural Deep Network Embedding
TLDR
This paper proposes a Structural Deep Network Embedding method, namely SDNE, which first proposes a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non- linear network structure and exploits the first-order and second-order proximity jointly to preserve the network structure.
LINE: Large-scale Information Network Embedding
TLDR
A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.
...
...