Graph-Level Embedding for Time-Evolving Graphs
arXiv:2306.01012 · doi:10.1145/3543873.3587299
Abstract
Graph representation learning (also known as network embedding) has been extensively researched with varying levels of granularity, ranging from nodes to graphs. While most prior work in this area focuses on node-level representation, limited research has been conducted on graph-level embedding, particularly for dynamic or temporal networks. However, learning low-dimensional graph-level representations for dynamic networks is critical for various downstream graph retrieval tasks such as temporal graph similarity ranking, temporal graph isomorphism, and anomaly detection. In this paper, we present a novel method for temporal graph-level embedding that addresses this gap. Our approach involves constructing a multilayer graph and using a modified random walk with temporal backtracking to generate temporal contexts for the graph's nodes. We then train a "document-level" language model on these contexts to generate graph-level embeddings. We evaluate our proposed model on five publicly available datasets for the task of temporal graph similarity ranking, and our model outperforms baseline methods. Our experimental results demonstrate the effectiveness of our method in generating graph-level embeddings for dynamic networks.
arXiv commentIn Companion Proceedings of the ACM Web Conference 2023
References in corpus (8)
- DeepWalk: Online Learning of Social Representations
- struc2vec: Learning Node Representations from Structural Identity
- graph2vec: Learning Distributed Representations of Graphs
- dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
- Learning Structural Node Embeddings Via Diffusion Wavelets
- DynGEM: Deep Embedding Method for Dynamic Graphs
- NetLSD: Hearing the Shape of a Graph
- Embedding Node Structural Role Identity into Hyperbolic Space