PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphs
arXiv:2007.10445
Abstract
Learning unsupervised node embeddings facilitates several downstream tasks such as node classification and link prediction. A node embedding is universal if it is designed to be used by and benefit various downstream tasks. This work introduces PanRep, a graph neural network (GNN) model, for unsupervised learning of universal node representations for heterogenous graphs. PanRep consists of a GNN encoder that obtains node embeddings and four decoders, each capturing different topological and node feature properties. Abiding to these properties the novel unsupervised framework learns universal embeddings applicable to different downstream tasks. PanRep can be furthered fine-tuned to account for possible limited labels. In this operational setting PanRep is considered as a pretrained model for extracting node embeddings of heterogenous graph data. PanRep outperforms all unsupervised and certain supervised methods in node classification and link prediction, especially when the labeled data for the supervised methods is small. PanRep-FT (with fine-tuning) outperforms all other supervised approaches, which corroborates the merits of pretraining models. Finally, we apply PanRep-FT for discovering novel drugs for Covid-19. We showcase the advantage of universal embeddings in drug repurposing and identify several drugs used in clinical trials as possible drug candidates.
References in corpus (17)
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- Learning deep representations by mutual information estimation and maximization
- MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding
- Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
- Learning Structural Node Embeddings Via Diffusion Wavelets
- Convolutional Neural Network Architectures for Signals Supported on Graphs
- Role Discovery in Networks
- Strategies for Pre-training Graph Neural Networks
- Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
- Reconstruction of Graph Signals through Percolation from Seeding Nodes
- DGL-KE: Training Knowledge Graph Embeddings at Scale
- Tensor Graph Convolutional Networks for Multi-relational and Robust Learning