Pre-training Graph Neural Networks
By Weihua Hu, Bowen Liu, Joseph Gomes, Marinka Zitnik, Percy Liang, Vijay S. Pande, Jure Leskovec. 2019
52 citations recorded by the source corpus.
Subfields: Graph Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Graph Learning
Citations in the corpus
- Graph-based, Self-Supervised Program Repair from Diagnostic Feedback (2020, background): “…% 47.4 47.4 49.1 The idea of using unlabeled data to networks has been shown effective across many fields, including computer vision (Vincent et al., 2008; Erhan et al., 2010), NLP (Peters et al., 2018; Devlin et al., 2019), graphs (Hu et al., 2020), and programming languages (Feng et al., 2020).”
- A Survey of Deep Learning for Scientific Discovery (2020, background): “Scientific Examples Graph neural networks have been very popular for several chemistry tasks, such as predicting molecular properties [53, 93, 67, 103], determining protein interfaces [60, 229] and even generating candidate molecules [41, 21].”
- Graph Contrastive Learning with Augmentations (2020, methodology): “Table 5: Transfer learning comparison with different manually designed pre-training schemes, where the compared numbers are from [9].”
- Self-Supervised Graph Transformer on Large-Scale Molecular Data (2020, methodology): “Contrast with [18], the molecular representations derived by our method are more appropriate in terms of persevering the domain knowledge, which has demonstrated remarkable effectiveness in downstream tasks without negative transfer.”
- InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization (2019, background): “Coming up with methods that are able to learn unsupervised representations of an entire graph, as opposed to nodes, is an important step in working with unlabeled or partially labeled graphs [36, 18, 39].”
- GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training (2020, methodology): “phs, differing from traditional network embeddings [14, 39–41, 47] and recent attempts on pre-training graph neural networks with attributed graphs as input and applying them within a specific domain [19]. 3.2 GCC Pre-Training Given a set of graphs, our goal is to pre-train a universal graph neural ”
- BERT Learns (and Teaches) Chemistry (2020, background): “Graph Neural Networks (namely, Graph Convolutional Networks and Graph Attention Networks) have been shown to be effective on toxicity tasks such as the Tox21 dataset [15, 33], and recently, pretraining procedures for graph neural networks have been shown to be effective on chemical inference [13].”