Variational Recurrent Neural Networks for Graph Classification

2019/02/07 by Edouard Pineau, Pineau, Edouard, Nathan de Lara +1
Computer Science · Materials Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning in Materials Science #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1902.02721

openalex publication_date 2019/02/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We address the problem of graph classification based only on structural information. Inspired by natural language processing techniques (NLP), our model sequentially embeds information to estimate class membership probabilities. Besides, we experiment with NLP-like variational regularization techniques, making the model predict the next node in the sequence as it reads it. We experimentally show that our model achieves state-of-the-art classification results on several standard molecular datasets. Finally, we perform a qualitative analysis and give some insights on whether the node prediction helps the model better classify graphs.

Citations

• Adam: A Method for Stochastic Optimization
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Feature-Based Classification of Networks
• Dynamics Based Features For Graph Classification
• graph2vec: Learning Distributed Representations of Graphs
• Learning Graph-Level Representations with Recurrent Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Related

• PiNet: A Permutation Invariant Graph Neural Network for Graph\n Classification
• Learning Graph Algorithms With Recurrent Graph Neural Networks
• Learning Graph-Level Representations with Recurrent Neural Networks
• Overcoming Order in Autoregressive Graph Generation
• Learning From Graph-Structured Data: Addressing Design Issues and Exploring Practical Applications in Graph Representation Learning