Memory-Based Graph Networks

February 21, 2020 · Entered Twilight · 🏛 International Conference on Learning Representations

"Last commit was 5.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: README.md, args.py, data, dataset.py, img, model.py, requirements.txt, train.py, utils.py

Authors Amir Hosein Khasahmadi, Kaveh Hassani, Parsa Moradi, Leo Lee, Quaid Morris arXiv ID 2002.09518 Category cs.LG: Machine Learning Cross-listed cs.NE, stat.ML Citations 99 Venue International Conference on Learning Representations Repository https://github.com/amirkhas/GraphMemoryNet ⭐ 104 Last Checked 1 month ago

Abstract

Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph. We also introduce two new networks based on this layer: memory-based GNN (MemGNN) and graph memory network (GMN) that can learn hierarchical graph representations. The experimental results shows that the proposed models achieve state-of-the-art results in eight out of nine graph classification and regression benchmarks. We also show that the learned representations could correspond to chemical features in the molecule data. Code and reference implementations are released at: https://github.com/amirkhas/GraphMemoryNet